EpubParser.java

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package mj.ocraptor.extraction.tika.parser.epub;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashSet;
import java.util.Set;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;

import mj.ocraptor.configuration.Config;
import mj.ocraptor.configuration.properties.ConfigBool;
import mj.ocraptor.extraction.image_processing.TikaImageHelper;
import mj.ocraptor.extraction.tika.parser.xml.DcXMLParser;
import mj.ocraptor.file_handler.filter.FileType;

import org.apache.commons.io.FilenameUtils;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.IOUtils;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AbstractParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.EmbeddedContentHandler;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

/**
 * Epub parser
 */
public class EpubParser extends AbstractParser {

  /** Serial version UID */
  private static final long serialVersionUID = 215176772484050550L;

  private static final Set<MediaType> SUPPORTED_TYPES = Collections
      .unmodifiableSet(new HashSet<MediaType>(Arrays.asList(
          MediaType.application("epub+zip"),
          MediaType.application("x-ibooks+zip"))));

  private Parser meta = new DcXMLParser();

  private Parser content = new EpubContentParser();

  public Parser getMetaParser() {
    return meta;
  }

  public void setMetaParser(Parser meta) {
    this.meta = meta;
  }

  public Parser getContentParser() {
    return content;
  }

  public void setContentParser(Parser content) {
    this.content = content;
  }

  public Set<MediaType> getSupportedTypes(ParseContext context) {
    return SUPPORTED_TYPES;
  }

  public void parse(InputStream stream, ContentHandler handler,
      Metadata metadata, ParseContext context) throws IOException,
      SAXException, TikaException {
    // Because an EPub file is often made up of multiple XHTML files,
    // we need explicit control over the start and end of the document
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    ContentHandler childHandler = new EmbeddedContentHandler(
        new BodyContentHandler(xhtml));

    ZipInputStream zip = new ZipInputStream(stream);
    ZipEntry entry = zip.getNextEntry();

    TikaImageHelper helper = new TikaImageHelper(metadata);
    try {
      while (entry != null) {
        // TODO: images
        String entryExtension = null;
        try {
          entryExtension = FilenameUtils.getExtension(new File(entry.getName())
              .getName());
        } catch (Exception e) {
          e.printStackTrace();
        }
        if (entryExtension != null
            && FileType.isValidImageFileExtension(entryExtension)
            && Config.inst().getProp(
                ConfigBool.ENABLE_IMAGE_OCR)) {
          File imageFile = null;
          try {
            imageFile = TikaImageHelper.saveZipEntryToTemp(zip, entry);
            helper.addImage(imageFile);
          } catch (Exception e) {
            e.printStackTrace();
          } finally {
            if (imageFile != null) {
              imageFile.delete();
            }
          }
        } else if (entry.getName().equals("mimetype")) {
          String type = IOUtils.toString(zip, "UTF-8");
          metadata.set(Metadata.CONTENT_TYPE, type);
        } else if (entry.getName().equals("metadata.xml")) {
          meta.parse(zip, new DefaultHandler(), metadata, context);
        } else if (entry.getName().endsWith(".opf")) {
          meta.parse(zip, new DefaultHandler(), metadata, context);
        } else if (entry.getName().endsWith(".html")
            || entry.getName().endsWith(".xhtml")) {
          content.parse(zip, childHandler, metadata, context);
        }
        entry = zip.getNextEntry();
      }
      helper.addTextToHandler(xhtml);
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      if (helper != null) {
        helper.close();
      }
    }

    // Finish everything
    xhtml.endDocument();
  }

}