branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'
        distribution: 'temurin'
    - uses: actions/cache@v4
      with:
        path: ~/.m2/repository

    branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'
        distribution: 'temurin'
    - uses: actions/cache@v4
      with:
        path: ~/.m2/repository

/**
 * A fault-tolerant wrapper for CrawlerClient that implements retry logic for failed requests.
 * This client will attempt to execute requests multiple times before giving up, with configurable
 * retry counts and intervals between attempts.
 *
 * <p>The client supports a RequestListener interface to monitor the request lifecycle and handle
 * exceptions during retries.</p>
 *

            CopyUtil.copy(is, fos);
        } catch (final Exception e) {
            CloseableUtil.closeQuietly(fos); // for deleting file
            FileUtil.deleteInBackground(tempFile); // clean up
            throw new CrawlingAccessException("Could not read a response body: " + responseData.getUrl(), e);
        } finally {
            CloseableUtil.closeQuietly(fos);
        }
        return tempFile;
    }

 * It also uses an AtomicBoolean to track whether the thread is running.
 * </p>
 *
 * <p>
 * The expired method is called when a timeout occurs.
 * It interrupts the running thread up to a maximum number of times.
 * The stop method is called to stop the timeout target.
 * </p>
 */
public class AccessTimeoutTarget implements TimeoutTarget {

 * 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
 * SuggestSettings settings = // Obtain SuggestSettings

            }
        }
    }

    /**
     * Cleans up the crawled data for a given session.
     * Deletes URL queue data and access result data, and clears the URL filter.
     * @param sessionId The session ID to clean up.
     */
    public void cleanup(final String sessionId) {
        // TODO transaction?
        urlQueueService.delete(sessionId);

    /**
     * Checks if the crawler container is available.
     *
     * @return true if the crawler container is available, false otherwise.
     */
    boolean available();

    /**
     * Cleans up resources and performs any necessary finalization tasks
     * before the object is destroyed. This method should be called to
     * ensure that all resources are properly released.
     */
    void destroy();

    /**

 * It uses Log4j2 for logging.
 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>
 *   <li>Getting content</li>
 *   <li>Handling redirects</li>
 *   <li>Processing responses</li>

        // Add entries
        statusMap.put(CrawlerStatus.INITIALIZING, "Starting up");
        statusMap.put(CrawlerStatus.RUNNING, "In progress");
        statusMap.put(CrawlerStatus.DONE, "Completed");

        // Verify entries
        assertEquals(3, statusMap.size());
        assertEquals("Starting up", statusMap.get(CrawlerStatus.INITIALIZING));