final String content = htmlXpathExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getHtml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;

                logger.warn("Failed to close HTTP client for API extractor", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_entity() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_entity.xml");

        } finally {
            xpathAPI.remove();
        }
    }

    /**
     * Extracts strings from a document using the specified XPath expression.
     *
     * @param document the DOM document to extract strings from
     * @param path the XPath expression to evaluate
     * @return an array of strings extracted from the document
     */

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import java.io.File;
import java.util.HashSet;
import java.util.Set;

class ClassMetaDataUtil {
    static void extractFromMetadata(File metaData, Set<String> excludedPackagePatterns, Action<ClassMetaData> extractor) {
        SimpleClassMetaDataRepository<ClassMetaData> repository = new SimpleClassMetaDataRepository<>();
        repository.load(metaData);

        final Set<String> excludedPrefixes = new HashSet<>();

        final Extractor extractor = new Extractor() {
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                return null;
            }
        };

        assertNull(extractorFactory.getExtractor("test"));
        extractorFactory.addExtractor("test", extractor);
        assertEquals(extractor, extractorFactory.getExtractor("test"));
    }

```

4. **Add tests**: Unit + integration

### Adding a Content Extractor

1. **Implement `Extractor`**:
```java
public class MyExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(InputStream in, Map<String, String> params) {
        ExtractData data = new ExtractData();
        // Extract text
        data.setContent(extractedText);
        return data;
    }
}