import org.codelibs.fess.crawler.exception.ExtractException;

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

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

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.

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

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

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

    /**

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 an input stream as plain text.
 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**

 * <li>{@link #indexFromQueryLog(QueryLog)} - Index from a single query log.
 * <li>{@link #indexFromQueryLog(QueryLog[])} - Index from multiple query logs.
 * <li>{@link #indexFromQueryLog(QueryLogReader, int, long)} - Index from query log reader with specified document per request and request interval.
 * <li>{@link #indexFromDocument(Map[])} - Index from an array of documents.

 */
package org.codelibs.fess.crawler.exception;

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors
 * to handle different scenarios such as wrapping another exception or providing a specific error message.

import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(ZipExtractor.class);

    /**
     * The archive stream factory.
     */

 *   <li>Offering a list of URLs to the queue, ensuring duplicates are not added.</li>
 *   <li>Polling (retrieving and removing) a URL from the queue.</li>
 *   <li>Saving the session (currently a no-op).</li>
 *   <li>Checking if a URL has already been visited.</li>
 *   <li>Generating URL queues from a previous session's access results.</li>
 * </ul>
 *
 * <p>

        return ROBOT_CONTEXT_THREAD_LOCAL.get();
    }

    /**
     * Sets the current {@link CrawlerContext} for the current thread.
     * If the provided {@code crawlerContext} is {@code null}, the context is removed from the thread-local storage.
     * Otherwise, the provided {@code crawlerContext} is set in the thread-local storage.
     *

import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * {@link ExtractorBuilder} is a builder class for creating and configuring an {@link ExtractData} object.
 * It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *

            }
        }
        return targetList;
    }

    /**
     * Extracts a field value from OpenSearch results and converts it to the specified type.
     *
     * @param <T> The target type.
     * @param field The field value from OpenSearch.
     * @param clazz The target class.
     * @return The converted field value.
     */
    @SuppressWarnings("unchecked")