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

/**
 * Extracts text content by executing an external command.
 */
public class CommandExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(CommandExtractor.class);

    /** The encoding for the output. */
    protected String outputEncoding = Constants.UTF_8;

    /** The extension for the output file. */

import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**
 * Represents extracted data from a crawled resource, including content and metadata.
 */
public class ExtractData
        implements TikaCoreProperties, CreativeCommons, Geographic, HttpHeaders, Message, ClimateForcast, TIFF, TikaMimeKeys, Serializable {

    private static final long serialVersionUID = 1L;

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

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

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

    /**

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;

    /**
     * Creates a new TextExtractor instance.
     */

import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * The {@link CrawlerContext} class holds the context information for a crawler execution.
 * It contains various attributes related to the crawler's state, configuration, and runtime data.
 * This class provides methods to access and modify these attributes, allowing for control and monitoring
 * of the crawler's behavior.
 *
 * <p>

import org.codelibs.core.stream.StreamUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * The FormScheme class implements the AuthScheme interface to provide
 * form-based authentication for HTTP clients. It handles the process of
 * obtaining a token and logging in using the provided credentials.
 *
 * <p>This class supports both GET and POST methods for token and login
 * requests. It also allows for the replacement of placeholders in URLs and

import jakarta.annotation.Resource;

/**
 * The {@code CrawlerThread} class represents a thread that executes the crawling process.
 * It is responsible for fetching URLs from the queue, accessing the content,
 * processing the response, and extracting child URLs.
 *
 * <p>
 * This class implements the {@link Runnable} interface, allowing it to be executed in a separate thread.

import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for RuleManager interface.
 * Tests the contract and behavior of RuleManager implementations.
 */
public class RuleManagerTest extends PlainTestCase {

    /**
     * Test implementation of RuleManager for testing purposes
     */
    public static class TestRuleManager implements RuleManager {

import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for AbstractTransformer.
 * Tests the abstract transformer implementation and its name management functionality.
 */
public class AbstractTransformerTest extends PlainTestCase {

    /**
     * Concrete implementation of AbstractTransformer for testing
     */
    public static class TestTransformer extends AbstractTransformer {

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();
    }

    /**