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 . file.
 *
 * @author shinsuke
 *
 */
public class MsPublisherExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPublisherExtractor instance.
     */
    public MsPublisherExtractor() {
        super();
    }

import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class TarExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(TarExtractorTest.class);

    public TarExtractor tarExtractor;

    @Override

import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class EmlExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(EmlExtractorTest.class);

    public EmlExtractor emlExtractor;

    @Override

package org.codelibs.fess.crawler.client.smb1;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class SmbClientTest extends PlainTestCase {

    public void test_doGet_accessTimeoutTarget() {
        SmbClient client = new SmbClient() {
            @Override

 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.
 * The extractor first tries to match against the URL, then falls back to the resource name if available.
 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

import java.io.StringReader;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.util.TextUtil.TextNormalizeContext;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 * @author kaorufuzita
 */
public class TextUtilTest extends PlainTestCase {

    public void test_getContent() {
        assertEquals("", normalizeText((String) null, 100, -1, -1, false));

 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */
    protected static final Pattern USER_AGENT_RECORD =

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

/**
 * This exception is thrown when an error occurs during OpenSearch access.
 *
 * @author shinsuke
 *
 */
public class OpenSearchAccessException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**
     * Creates a new instance of OpenSearchAccessException.

import org.apache.http.auth.AuthSchemeProvider;
import org.apache.http.impl.auth.NTLMScheme;
import org.apache.http.protocol.HttpContext;

/**
 * This class is AuthSchemeFactory implementation for NTLM.
 *
 * @author shinsuke
 *
 */
public class NTLMSchemeProvider implements AuthSchemeProvider {

    /**
     * Creates a new NTLMSchemeProvider instance.
     */
    public NTLMSchemeProvider() {
        super();
    }

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
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * Creates a new MsWordExtractor instance.
     */
    public MsWordExtractor() {
        super();
    }