* </p>
 *
 */
public abstract class AbstractExtractor implements Extractor {

    /** The crawler container. */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * Constructs a new AbstractExtractor.
     */
    public AbstractExtractor() {
        // NOP
    }

    /**
     * Registers this extractor with the ExtractorFactory.

/**
 * Test class for AbstractExtractor base functionality.
 * Focuses on testing the validateInputStream() method and other common functionality.
 */
public class AbstractExtractorTest extends PlainTestCase {

    /**
     * Concrete test implementation of AbstractExtractor for testing purposes.
     */
    private static class TestExtractor extends AbstractExtractor {
        private boolean validateCalled = false;

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

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

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

    /**
     * Extracts text from the Visio input stream.

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();
    }

    /**
     * Extracts text from the PowerPoint input stream.

import org.codelibs.fess.crawler.entity.ExtractData;
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.
     */
    public TextExtractor() {

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.

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();
    }

    /**
     * Extracts text from the Word input stream.

 *
 * <p>The filename is retrieved from the {@link ExtractData#RESOURCE_NAME_KEY} parameter.
 * If this parameter is not present, an empty string is returned as the content.</p>
 */
public class FilenameExtractor extends AbstractExtractor {

    /**
     * Constructs a new FilenameExtractor.
     */
    public FilenameExtractor() {
        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.

- ✅ Handles empty archives gracefully
- ✅ Mixed valid/invalid entries processed correctly
- ✅ Null input stream validation

---

### 4. AbstractExtractorTest.java
**Purpose**: Test the base AbstractExtractor functionality.

**Key Test Areas**:
- `validateInputStream()` method behavior
- Exception types and messages
- Stream consumption (should not consume)
- Consistency across multiple calls

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();
    }

    /**
     * Extracts text from the Publisher input stream.