// 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

            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

 *
 * <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 {

 * </p>
 *
 */
public class DataServiceImpl implements DataService<AccessResultImpl<Long>> {

    /** Counter for generating unique IDs */
    protected static volatile long idCount = 0L;

    /** Lock object for synchronizing access to idCount */
    private static Object idCountLock = new Object();

    /** Helper for managing access result data in memory */
    @Resource
    protected MemoryDataHelper dataHelper;

#FESS_JAVA_OPTS="$FESS_JAVA_OPTS -Djavax.net.ssl.trustStorePassword=changeit"

# min and max heap sizes should be set to the same value to avoid
# stop-the-world GC pauses during resize, and so that we can lock the
# heap in memory on startup to prevent any of it from being swapped
# out.
FESS_JAVA_OPTS="$FESS_JAVA_OPTS -Xms${FESS_MIN_MEM}"
FESS_JAVA_OPTS="$FESS_JAVA_OPTS -Xmx${FESS_MAX_MEM}"

set FESS_MIN_MEM=%FESS_HEAP_SIZE%
set FESS_MAX_MEM=%FESS_HEAP_SIZE%
)

REM min and max heap sizes should be set to the same value to avoid
REM stop-the-world GC pauses during resize, and so that we can lock the
REM heap in memory on startup to prevent any of it from being swapped
REM out.
set FESS_JAVA_OPTS=%FESS_JAVA_OPTS% -Xms%FESS_MIN_MEM% -Xmx%FESS_MAX_MEM%

        return viewHelper.getActionHook().hookBefore(runtime, super::hookBefore);
    }

    /**
     * Hook method called in the finally block of action processing.
     * This method delegates to the view helper's action hook for final cleanup.
     *
     * @param runtime the action runtime context
     */
    @Override

import org.codelibs.jcifs.smb.impl.SmbFileInputStream;

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>
 * This client supports authentication, content retrieval, and metadata extraction from SMB files.

        } finally {
            if (task != null) {
                task.cancel();
            }
            if (p != null && p.isAlive()) {
                logger.warn("Process {} is still alive in finally block. Forcing destruction.", p);
                if (task == null) {
                    task = new ProcessDestroyer(p, ist, commandDestroyTimeout);
                }
                if (!task.isExecuted()) {