* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor;

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

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * @author shinsuke
 *
 */
public interface Extractor {

    ExtractData getText(InputStream in, Map<String, String> params);

    protected Map<String, Extractor> extractorMap = new HashMap<>();

    public void addExtractor(final String key, final Extractor extractor) {
        if (StringUtil.isBlank(key)) {
            throw new CrawlerSystemException("The key is null.");
        }
        if (extractor == null) {
            throw new CrawlerSystemException("The extractor is null.");
        }
        extractorMap.put(key, extractor);

        final CommandExtractor extractor = new CommandExtractor();
        extractor.executionTimeout = 1000L;
        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        try {
            final ExtractData data = extractor.getText(new FileInputStream(contentFile), params);
            fail(data.toString());

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.exception.FessSystemException;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

 * 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.codelibs.fess.crawler.extractor.impl;

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

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_entity() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_entity.xml");

import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * Gets a text from .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {

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

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

import org.apache.poi.hslf.usermodel.HSLFShape;
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;