mvn license:format

# Generate test coverage report
mvn jacoco:prepare-agent test jacoco:report

# Generate API documentation
mvn javadoc:javadoc
```

### Testing

The project uses JUnit 4 with embedded OpenSearch for integration testing:

```bash
# Run all tests
mvn test

# Run specific test class
mvn test -Dtest=SuggesterTest

# Run with verbose output

 *     <li>Handle duplicated file paths by appending a counter.</li>
 *     <li>Store the file path in the result data.</li>
 *     <li>Retrieve the stored file as a File object.</li>
 * </ul>
 *
 * <p>
 * The class uses several configurable properties to customize the file storage behavior,
 * such as the base path, replacement strings for special characters in URLs,

    @Test
    @DisplayName("readAndXWireFormat reads chained plain SMB and marks received")
    void testReadAndXWireFormatWithPlainSMB() {
        DummyPlainSMB next = new DummyPlainSMB();
        // The implementation uses andx.wordCount, which starts at 0 by default
        // We need to test the actual behavior where wordCount is 0
        // This means readParameterWordsWireFormat won't be called (line 282-284)

 * processing the response, and extracting child URLs.
 *
 * <p>
 * This class implements the {@link Runnable} interface, allowing it to be executed in a separate thread.
 * It uses various services and components, such as {@link UrlQueueService}, {@link DataService},
 * {@link CrawlerContainer}, {@link LogHelper}, {@link CrawlerClientFactory}, and {@link CrawlerContext},
 * to perform its tasks.
 * </p>
 *

        // Test with no auth - should request Basic
        when(request.getHeader("Authorization")).thenReturn(null);

        networkExplorer.doGet(request, response);

        // NetworkExplorer uses addHeader for Basic auth
        verify(response).addHeader("WWW-Authenticate", "Basic realm=\"TestRealm\"");
        verify(response).setStatus(HttpServletResponse.SC_UNAUTHORIZED);
    }

    /**

 * This class provides functionality to track, record, and report statistics
 * about crawler operations including timing data, performance metrics, and
 * operational events. It uses an internal cache to maintain statistics
 * objects and provides methods to begin tracking, record events, and
 * finalize statistics collection.
 *
 */
public class CrawlerStatsHelper {

    /**

        } catch (CrawlingAccessException e) {
            assertTrue(e.getCause() instanceof InterruptedException);
        }
    }

    public void test_temp_file_creation() {
        // Test that temp file uses correct prefix "S3Client" not "StorageClient"
        S3Client client = new S3Client() {
            @Override
            protected java.io.File createTempFile(String prefix, String suffix, java.io.File directory) {

        assertNotNull(newWriter);
    }

    @Test
    public void test_writeItemsUsesSettingsTimeout() throws Exception {
        // This test verifies that the writer uses settings.getIndexTimeout()
        // instead of a hardcoded timeout value
        String[][] readings = new String[1][];
        readings[0] = new String[] { "test" };

// Add file URL
crawler.addUrl("file:///path/to/directory");
crawler.urlFilter.addInclude("file:///path/to/directory/.*");
```

## Configuration

### XML Configuration

Fess Crawler uses XML-based configuration with LastaFlute DI. Place configuration files in your classpath:

```xml
<!-- crawler.xml -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"

            assertEquals("Users", aliasBuiltin.toDisplayString());
        }

        @Test
        @DisplayName("toString uses hex authority when high bytes are non-zero")
        void testToStringHexAuthority() {
            byte[] ident = new byte[] { 1, 2, 3, 4, 5, 6 }; // high bytes non-zero -> hex representation