com.day.cq.dam.handler.standard.ooxml.OpenOfficeHandler Maven / Gradle / Ivy

Go to download
/*
 * Copyright 1997-2011 Day Management AG
 * Barfuesserplatz 6, 4001 Basel, Switzerland
 * All Rights Reserved.
 *
 * This software is the confidential and proprietary information of
 * Day Management AG, ("Confidential Information"). You shall not
 * disclose such Confidential Information and shall use it only in
 * accordance with the terms of the license agreement you entered into
 * with Day.
 */
package com.day.cq.dam.handler.standard.ooxml;

import java.awt.Dimension;
import java.awt.image.BufferedImage;
import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import javax.xml.parsers.DocumentBuilderFactory;

import org.apache.commons.io.IOUtils;
import org.apache.felix.scr.annotations.Component;
import org.apache.felix.scr.annotations.Reference;
import org.apache.felix.scr.annotations.ReferencePolicy;
import org.apache.felix.scr.annotations.Service;
import org.apache.sling.commons.mime.MimeTypeService;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.traversal.DocumentTraversal;
import org.w3c.dom.traversal.NodeFilter;
import org.w3c.dom.traversal.NodeIterator;

import com.day.cq.dam.api.Asset;
import com.day.cq.dam.api.Rendition;
import com.day.cq.dam.api.metadata.ExtractedMetadata;
import com.day.cq.dam.commons.handler.AbstractAssetHandler;
import com.day.image.Layer;
import com.day.cq.dam.commons.xml.DocumentBuilderFactoryProvider;

/**
 * Open Office metadata handler service
 * */
@Component(inherit = true, metatype = false)
@Service
public class OpenOfficeHandler extends AbstractAssetHandler {

    private static final Logger log = LoggerFactory.getLogger(OpenOfficeHandler.class);

    public static final String MIMETYPE_DOCX
            = "application/vnd.openxmlformats-officedocument.wordprocessingml.document";
    public static final String MIMETYPE_XLSX
            = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet";
    public static final String[] MIMETYPES_SUPPORTED = new String[] {MIMETYPE_DOCX, MIMETYPE_XLSX};

    // zip entries containing meta data
    private static final String ENTRY_CORE = "docProps/core.xml";
    private static final String ENTRY_APP = "docProps/app.xml";
    //todo this needs to be tested with documents created on windows. (PNG vs JPEG)
    private static final String ENTRY_THUMBNAIL = "docProps/thumbnail.jpeg";
    private static final String ENTRY_THUMBNAIL_EMF = "docProps/thumbnail.emf";

    @Reference(policy = ReferencePolicy.STATIC)
    protected MimeTypeService mimeTypeService;
    
    private static final String META_KEY_THUMBNAIL = "thumbnail";

    public ExtractedMetadata extractMetadata(final Asset asset) {
        final ZipInputStream zis = new ZipInputStream(new BufferedInputStream(asset.getOriginal().getStream()));
        final ExtractedMetadata metadata = new ExtractedMetadata();
        try {
            readEntries(zis, metadata, asset);
        } catch (Exception e) {
            log.warn("Failed to extract metadata for {} reason: {}", asset.getPath(), e.getMessage());
            log.debug("Stack Trace: ", e);
        } finally {
            IOUtils.closeQuietly(zis);
        }
        setMimetype(metadata, asset);
        return metadata;
    }

    public BufferedImage getImage(final Rendition rendition) throws IOException {
        return getImage(rendition, null);
    }

    public BufferedImage getImage(final Rendition rendition, final Dimension dim) throws IOException {
        final Asset asset = rendition.getAsset();
        final byte[] picture = (byte[]) extractMetadata(asset).getProperty(META_KEY_THUMBNAIL);
        // if we have an embedded image
        if (picture != null) {
            return new Layer(new ByteArrayInputStream(picture), dim).getImage();
        }
        // according to the spec, a thumbnail representation of a document should be generated by default when the
        // file is saved.
        log.warn("Failed to retrieve thumbnail for {}", asset.getPath());
        return null;
    }

    /**
     * {@inheritDoc}
     */
    public String[] getMimeTypes() {
        return MIMETYPES_SUPPORTED;
    }

    /* all private methods */
    private void readEntries(final ZipInputStream zis, final ExtractedMetadata metadata, final Asset asset) throws Exception {
        ZipEntry entry;
        while ((entry = zis.getNextEntry()) != null) {
            final String name = entry.getName();
            if (name.equals(ENTRY_CORE) || name.equals(ENTRY_APP)) {
                ByteArrayOutputStream out = new ByteArrayOutputStream();
                IOUtils.copy(zis, out);
                // build xml document to extract meta info
                DocumentBuilderFactoryProvider factoryprovider = new DocumentBuilderFactoryProvider();
                DocumentBuilderFactory documentBuilderFactory = factoryprovider.createSecureBuilderFactory(true);
                Document document = documentBuilderFactory.newDocumentBuilder()
                        .parse(new ByteArrayInputStream(out.toByteArray()));
                IOUtils.closeQuietly(out);
                DocumentTraversal dt = (DocumentTraversal) document;
                NodeIterator nit = dt.createNodeIterator(document, NodeFilter.SHOW_ELEMENT, null, true);
                nit.nextNode(); // skip first node
                Element next;
                while ((next = (Element) nit.nextNode())!=null) {
                    metadata.setMetaDataProperty(next.getLocalName(), next.getTextContent());
                }
            } else if (name.equals(ENTRY_THUMBNAIL)) {
                ByteArrayOutputStream out = new ByteArrayOutputStream();
                try{
                	IOUtils.copy(zis, out);
                	metadata.setProperty(META_KEY_THUMBNAIL, out.toByteArray());
                }finally{
                	IOUtils.closeQuietly(out);
                }
			} else if (name.equals(ENTRY_THUMBNAIL_EMF)) {
                ByteArrayOutputStream out = new ByteArrayOutputStream();
                String mimeType = mimeTypeService.getMimeType(name);
                try{
                    IOUtils.copy(zis, out);
                    asset.addRendition("thumbnail.emf", new ByteArrayInputStream(out.toByteArray()),
                        mimeType);
                }finally{
                    IOUtils.closeQuietly(out);
                }
				// TODO Handle EMF format file in a better way
                // below code was creating circular reference with AssetStore
                //AssetHandler handler = store.getAssetHandler(mimeType);
				//BufferedImage img = handler.getImage(rend);
				//if (img != null) {
				//	ByteArrayOutputStream baos = new ByteArrayOutputStream();
				//	try	{
				//		ImageIO.write(img,JPEG_FORMAT , baos);
				//		baos.flush();
				//		metadata.setProperty(META_KEY_THUMBNAIL, baos.toByteArray());
				//	}finally{
				//		IOUtils.closeQuietly(baos);
				//	}
				// } else {
				//	log.info("Cannot extract image from EMF format");
				// }
			}
        }
    }

}