org.apache.tika.parser.hwp.HwpV5Parser Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of tika-parsers Show documentation
There is a newer version: 3.1.0
/*
 * 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 org.apache.tika.parser.hwp;

import java.io.IOException;
import java.io.InputStream;
import java.util.Collections;
import java.util.Set;

import org.apache.tika.exception.TikaException;
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.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

public class HwpV5Parser extends AbstractParser {

    private static final long serialVersionUID = 1L;

    private static final Set SUPPORTED_TYPES = Collections.singleton(MediaType.application("x-hwp-v5"));
    public static final String HWP_MIME_TYPE = "application/x-hwp-v5";

    private HwpTextExtractorV5 extractor;

    public HwpV5Parser() {
        extractor = new HwpTextExtractorV5();
    }

    @Override
    public Set getSupportedTypes(ParseContext context) {
        return SUPPORTED_TYPES;
    }

    @Override
    public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {

        metadata.set(Metadata.CONTENT_TYPE, HWP_MIME_TYPE);

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

        try {
            extractor.extract(stream, metadata, xhtml);
        } finally {
            xhtml.endDocument();
        }
    }

}