import org.apache.poi.hslf.usermodel.HSLFSlideShow;
import org.apache.poi.hslf.usermodel.HSLFTextParagraph;
import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */

     */
    public TextExtractor() {
        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            return new ExtractData(new String(InputStreamUtil.getBytes(in), getEncoding()));
        } catch (final Exception e) {

            executeCommand(inputFile, outputFile);

            final ExtractData extractData = new ExtractData(new String(FileUtil.readBytes(outputFile), outputEncoding));
            if (StringUtil.isNotBlank(resourceName)) {
                extractData.putValues("resourceName", new String[] { resourceName });
            }

            return extractData;
        } catch (final IOException e) {

     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final VisioTextExtractor visioTextExtractor = new VisioTextExtractor(in);
            return new ExtractData(visioTextExtractor.getText());

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;

            throw new ExtractException(e);
        }
    }

    /**
     * Creates an ExtractData object from the extracted content.
     * @param content The extracted content.
     * @return The ExtractData object.
     */
    protected ExtractData createExtractData(final String content) {
        return new ExtractData(extractString(content));
    }

    /**
     * Detects the encoding of the input stream.

     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**
     * Returns the weight of the extractor.
     * The default implementation returns a weight of 1.
     *

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */

            final MimeMessage message = new MimeMessage(mailSession, in);
            final String content = getBodyText(message);
            final ExtractData data = new ExtractData(content != null ? content : StringUtil.EMPTY);
            final Enumeration<Header> headers = message.getAllHeaders();
            while (headers.hasMoreElements()) {

package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke
 *
 */