final ExtractData extractData = markdownExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        final String content = extractData.getContent();

        // Code blocks should be converted to plain text
        assertTrue(content.contains("public class Example") || content.contains("Example"));
    }

         */
        public boolean isRunning() {
            return running;
        }

        /**
         * Waits for the crawling thread to terminate.
         * This method blocks until the thread completes its execution.
         * Interrupted exceptions are caught and logged at debug level.
         */
        public void awaitTermination() {
            try {
                join();

    protected List<IntervalRule> ruleList = new ArrayList<>();

    /**
     * Checks the crawler status and waits if the crawler is not running.
     * This method blocks until the crawler is running again.
     */
    public void checkCrawlerStatus() {
        while (!crawlerRunning) {
            ThreadUtil.sleepQuietly(crawlerWaitMillis);
        }
    }

    /**

**DI**: LastaFlute container with `@Resource` and XML config

### Core Principles

**Thread Safety**:
- `AtomicLong` for counters (`CrawlerContext.accessCount`)
- `volatile` for status flags
- Synchronized blocks for critical sections
- Thread-local storage via `CrawlingParameterUtil`

**Resource Management**:
- `AutoCloseable` throughout
- `DeferredFileOutputStream` for large responses (temp files for >1MB)

            return QueryBuilders.matchPhraseQuery(f, text);
        }

        final UnicodeBlock block = UnicodeBlock.of(text.codePointAt(0));
        if (block == UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS //
                || block == UnicodeBlock.HIRAGANA //
                || block == UnicodeBlock.KATAKANA //
                || block == UnicodeBlock.HANGUL_SYLLABLES //
        ) {
            return QueryBuilders.prefixQuery(f, text);

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 {
    public static void main(String[] args) {
        System.out.println("Hello, World!");
    }
}
```

## Links

        // Disallow: /*.pdf$ - should block .pdf files but not .pdf with query params
        assertFalse(robotsTxt.allows("/document.pdf", "WildcardBot"));
        assertFalse(robotsTxt.allows("/files/report.pdf", "WildcardBot"));
        assertTrue(robotsTxt.allows("/document.pdf?download=true", "WildcardBot")); // $ means exact end

        // Disallow: /admin/*.php - should block PHP files in admin directory

        final Path baseDir = tempFolder.getRoot().toPath();
        final Path traversalPath = baseDir.resolve("../../../etc/passwd");

        assertFalse("Path traversal should be blocked", FileUtil.isPathSafe(traversalPath, baseDir));
    }

    /**
     * Test isPathSafe with File objects
     *
     * @throws Exception
     */
    @Test

                throw new JobNotFoundException("Process for " + sessionId + " is not running.");
            }
        }

        // Perform I/O operations outside synchronized block to avoid blocking other threads
        try {
            final OutputStream out = process.getOutputStream();
            IOUtils.write(command + "\n", out, Constants.CHARSET_UTF_8);
            out.flush();

 *
 * <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>
 * </ul>
 */
public class MarkdownExtractor extends AbstractExtractor {