}

    /**
     * Test extraction with null parameters map.
     */
    public void test_getText_withNullParams() {
        final InputStream in = new ByteArrayInputStream(new byte[0]);

        final ExtractData result = filenameExtractor.getText(in, null);

        assertNotNull(result);
        assertEquals("", result.getContent());
    }

    /**
     * Test extraction with empty parameters map.
     */

            assertTrue("Error message should indicate extraction failure", e.getMessage().contains("Failed to extract"));
        } finally {
            // Reset to default encoding
            textExtractor.setEncoding("UTF-8");
        }
    }

    /**
     * Test extraction with empty input stream.
     */
    public void test_getText_emptyInputStream_returnsEmptyContent() {

 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Structured text extraction with key-value pairs</li>
 *   <li>Top-level field extraction as metadata</li>
 *   <li>Nested structure flattening with configurable depth</li>
 *   <li>Array element extraction</li>
 *   <li>Configurable field separator and array formatting</li>
 * </ul>

 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>YAML front matter metadata extraction</li>
 *   <li>Heading structure extraction</li>
 *   <li>Link URL extraction</li>
 *   <li>Code block content extraction</li>
 *   <li>Clean text conversion from Markdown</li>
 *   <li>Configurable encoding</li>

     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null
     * @throws ExtractException if an error occurs during extraction
     * @throws MaxLengthExceededException if the extracted content size exceeds the maximum limit
     */
    @Override

    /**
     * Default character encoding for content extraction.
     */
    protected String encoding = Constants.UTF_8;

    /**
     * The preload size for charset detection.
     */
    protected int preloadSizeForCharset = 2048;

    /**
     * Indicates whether comment tags should be ignored during extraction.
     */
    protected boolean ignoreCommentTag = false;

    /**

**Key Test Areas**:
- Resource closure on successful extraction (MS Office extractors)
- Resource closure on failed extraction
- Improved error messages with context
- Input validation using `validateInputStream()`

**Covered Extractors**:
- MsWordExtractor
- MsExcelExtractor
- MsPowerPointExtractor
- TextExtractor

**Test Count**: 8 tests

**Key Scenarios**:
- ✅ Successful extraction closes resources properly

            // Test file name extraction
            assertEquals("file.txt", new SmbFile("smb1://server/share/file.txt").getName());
            // Test directory name extraction (should include trailing slash)
            assertEquals("dir/", new SmbFile("smb1://server/share/dir/").getName());
            // Test share name extraction
            assertEquals("share/", new SmbFile("smb1://server/share/").getName());

  - crawler
  - extractor
  - markdown
---

# Introduction

This is a sample Markdown document for testing the MarkdownExtractor.

## Features

The extractor should handle:

- YAML front matter extraction
- Heading structure
- **Bold text** and *italic text*
- Lists and other formatting

### Code Examples

Here is some inline `code` and a code block:

```java
public class Example {

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

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */
public class UnsupportedExtractException extends ExtractException {

    private static final long serialVersionUID = 1L;