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

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
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 PdfExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(PdfExtractorTest.class);

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

/**
 * @author shinsuke
 *
 */
public class ExtractorFactoryTest extends PlainTestCase {
    public ExtractorFactory extractorFactory;

    @Override

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class RuleManagerImplTest extends PlainTestCase {
    public RuleManager ruleManager;

    @Override
    protected void setUp() throws Exception {

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Enhanced test class for TextExtractor covering improved error messages and edge cases.
 */
public class TextExtractorEnhancedTest extends PlainTestCase {

import java.io.IOException;
import java.io.Reader;
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() {

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

```

### Run tests for specific extractor:
```bash
mvn test -Dtest=MsWordExtractorTest,ExtractorResourceManagementTest
```

## Test Requirements

### Dependencies:
- JUnit 4.x
- DBFlute UTFlute (PlainTestCase)
- Apache POI (for MS Office tests)
- Apache Commons Compress (for archive tests)

### Test Resources:
- `extractor/msoffice/test.doc`
- `extractor/msoffice/test.xls`

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

import java.util.regex.Pattern;

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

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

    public void test_match_default() {
        final RegexRule regexRule = new RegexRule();

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for MarkdownExtractor.
 */
public class MarkdownExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(MarkdownExtractorTest.class);