TextParser.java

/**   
 * License Agreement for OpenSearchServer
 *
 * Copyright (C) 2010-2015 Emmanuel Keller / Jaeksoft
 * 
 * http://www.open-search-server.com
 * 
 * This file is part of OpenSearchServer.
 *
 * OpenSearchServer is free software: you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 *  (at your option) any later version.
 *
 * OpenSearchServer is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with OpenSearchServer. 
 *  If not, see <http://www.gnu.org/licenses/>.
 **/

package com.jaeksoft.searchlib.parser;

import com.ibm.icu.text.CharsetDetector;
import com.ibm.icu.text.CharsetMatch;
import com.jaeksoft.searchlib.SearchLibException;
import com.jaeksoft.searchlib.analysis.ClassPropertyEnum;
import com.jaeksoft.searchlib.analysis.LanguageEnum;
import com.jaeksoft.searchlib.streamlimiter.StreamLimiter;
import com.jaeksoft.searchlib.util.IOUtils;

import java.io.BufferedInputStream;
import java.io.IOException;

public class TextParser extends Parser {

	public static final String[] DEFAULT_MIMETYPES = { "text/plain" };

	public static final String[] DEFAULT_EXTENSIONS = { "txt" };

	private static ParserFieldEnum[] fl = { ParserFieldEnum.parser_name,
			ParserFieldEnum.content };

	public TextParser() {
		super(fl);
	}

	@Override
	public void initProperties() throws SearchLibException {
		super.initProperties();
		addProperty(ClassPropertyEnum.SIZE_LIMIT, "0", null, 20, 1);
	}

	@Override
	protected void parseContent(StreamLimiter streamLimiter, LanguageEnum lang)
			throws IOException {
		CharsetDetector detector = new CharsetDetector();
		BufferedInputStream bis = null;
		try {
			bis = new BufferedInputStream(streamLimiter.getNewInputStream());
			detector.setText(bis);
			CharsetMatch match = detector.detect();
			String content;
			if (match != null)
				content = match.getString();
			else
				content = IOUtils.toString(streamLimiter.getNewInputStream(), "UTF-8");
			ParserResultItem result = getNewParserResultItem();
			result.addField(ParserFieldEnum.content, content);
			result.langDetection(10000, ParserFieldEnum.content);
		} finally {
			IOUtils.close(bis);
		}
	}
}