# Build without tests
mvn clean install -DskipTests

# Build specific module
mvn clean install -pl fess-crawler

# Generate test coverage report
mvn jacoco:report
```

### Code Quality

```bash
# Format code
mvn formatter:format

# Update license headers
mvn license:format

# Run static analysis
mvn spotbugs:check
```

### Running Tests

```bash
# Run all tests

        if (successfulHttpCodes == null) {
            return true;
        }
        final int httpStatusCode = responseData.getHttpStatusCode();
        for (final int code : successfulHttpCodes) {
            if (code == httpStatusCode) {
                return true;
            }
        }
        return false;
    }

    /**

            return minioClient.statObject(args);
        } catch (final ErrorResponseException e) {
            final String code = e.errorResponse().code();
            switch (code) {
            case "NoSuchBucket":
                throw new CrawlingAccessException("Bucket " + bucketName + " is not found.", e);
            case "NoSuchKey", "NoSuchObject":

 * or a fixed number. It also allows filtering documents based on their size, using the {@code limitOfDocumentSize}
 * parameter.
 * </p>
 *
 * <p>
 * The reader uses a queue to buffer documents read from Elasticsearch, and it retries failed requests
 * up to a maximum number of times.
 * </p>
 *
 * <p>
 * <b>Usage:</b>
 * </p>
 * <pre>
 * {@code
 * Client client = // Obtain Elasticsearch client

 *   <li>Managing singleton instances with lifecycle hooks</li>
 *   <li>Creating prototype instances on demand</li>
 *   <li>Dependency injection using {@code @Resource} annotation</li>
 *   <li>Lifecycle management using {@code @PostConstruct} and {@code @PreDestroy} annotations</li>
 * </ul>
 *
 * <p>Components can be registered in two ways:
 * <ul>

 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.
 * </p>
 *
 * <p>
 * The handler relies on environment variables for configuration:
 * </p>
 * <ul>
 *   <li>{@code STORAGE_ENDPOINT}: The endpoint URL of the MinIO service.</li>
 *   <li>{@code STORAGE_ACCESS_KEY}: The access key for authentication.</li>

 * </ol>
 *
 * <p>
 * The thread also manages the active thread count using {@code crawlerContext.activeThreadCountLock}
 * and provides methods for logging messages using {@link LogHelper}.
 * </p>
 *
 * <p>
 * The crawling process continues until the crawler status is {@link CrawlerStatus#DONE} or the
 * {@link #isContinue(int)} method returns {@code false}.
 * </p>
 *
 */
public class CrawlerThread implements Runnable {

        super();
    }

    /**
     * Gets the HTTP status code of the response.
     *
     * @return the HTTP status code
     */
    public int getHttpStatusCode() {
        return httpStatusCode;
    }

    /**
     * Sets the HTTP status code of the response.
     *
     * @param statusCode the HTTP status code to set
     */
    public void setHttpStatusCode(final int statusCode) {

 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.
 * The default value for {@code targetNodePath} is "//HTML/BODY | //@alt | //@title", which selects the body of the HTML document,
 * as well as the alt and title attributes.
 * </p>
 * <p>

      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.