BoilerpipeSAXInput.java

/**
 * Copyright (C) 2013 Christian Kohlschütter (ckkohl79@gmail.com)
 *
 * Licensed 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 de.l3s.boilerpipe.sax;

import java.io.IOException;

import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

import de.l3s.boilerpipe.BoilerpipeInput;
import de.l3s.boilerpipe.BoilerpipeProcessingException;
import de.l3s.boilerpipe.document.TextDocument;

/**
 * Parses an {@link org.xml.sax.InputSource} using SAX and returns a {@link TextDocument}.
 * 
 * @author Christian Kohlschütter
 */
public final class BoilerpipeSAXInput implements BoilerpipeInput {
    private final InputSource is;

    /**
     * Creates a new instance of {@link de.l3s.boilerpipe.sax.BoilerpipeSAXInput} for the given {@link org.xml.sax.InputSource}.
     *
     * @param is
     * @throws org.xml.sax.SAXException
     */
    public BoilerpipeSAXInput(final InputSource is) throws SAXException {
        this.is = is;
    }

    /**
     * Retrieves the {@link TextDocument} using a default HTML parser.
     */
    public TextDocument getTextDocument() throws BoilerpipeProcessingException {
        return getTextDocument(new BoilerpipeHTMLParser());
    }
    
    /**
     * Retrieves the {@link TextDocument} using the given HTML parser.
     * 
     * @param parser The parser used to transform the input into boilerpipe's internal representation.
     * @return The retrieved {@link TextDocument}
     * @throws BoilerpipeProcessingException
     */
    public TextDocument getTextDocument(final BoilerpipeHTMLParser parser) throws BoilerpipeProcessingException {
        try {
            parser.parse(is);
        } catch (IOException e) {
            throw new BoilerpipeProcessingException(e);
        } catch (SAXException e) {
            throw new BoilerpipeProcessingException(e);
        }
        
        return parser.toTextDocument();
    }

}