}

// Wait for completion
crawler.awaitTermination();
System.out.println("Crawling completed");
```

### Custom Content Extractor

```java
public class CustomExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(final InputStream inputStream, final Map<String, String> params) {
        // Custom extraction logic
        ExtractData extractData = new ExtractData();

import org.codelibs.fess.opensearch.user.allcommon.EsAbstractEntity;
import org.codelibs.fess.opensearch.user.bsentity.dbmeta.UserDbm;

/**
 * ${table.comment}
 * @author ESFlute (using FreeGen)
 */
public class BsUser extends EsAbstractEntity {

    // ===================================================================================
    //                                                                          Definition

import org.opensearch.index.query.functionscore.FunctionScoreQueryBuilder.FilterFunctionBuilder;

/**
 * @author ESFlute (using FreeGen)
 */
public abstract class BsGroupCQ extends EsAbstractConditionQuery {

    protected static final Class<?> suppressUnusedImportLocalDateTime = LocalDateTime.class;

    // ===================================================================================

import java.util.regex.MatchResult;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Checks adoc files for broken links.
 */
@CacheableTask
public abstract class FindBrokenInternalLinks extends DefaultTask {

    // <<groovy_plugin.adoc#groovy_plugin,Groovy>>
    private final Pattern linkPattern = Pattern.compile("<<([^,>]+)[^>]*>>");
    // groovy_plugin.adoc#groovy_plugin,Groovy

/**
 * Default implementation of RankFusionSearcher that performs standard OpenSearch queries.
 * This searcher handles query execution, response processing, and document highlighting.
 */
public class DefaultSearcher extends RankFusionSearcher {

    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(DefaultSearcher.class);

    /**
     * Creates a new instance of DefaultSearcher.

import com.google.common.base.Charsets;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

    private static final Logger logger = LogManager.getLogger(ApiExtractor.class);

    /** The URL of the API endpoint. */
    protected String url;

    /** The access timeout in seconds. */

 *
 * @author David Beaumont
 * @since 15.0
 */
@GwtCompatible
@SuppressWarnings("EscapedEntity") // We do mean for the user to see "&" etc.
public abstract class ArrayBasedUnicodeEscaper extends UnicodeEscaper {
  // The replacement array (see ArrayBasedEscaperMap).
  private final char[][] replacements;
  // The number of elements in the replacement array.
  private final int replacementsLength;

/**
 * A non-public interface for the methods shared between {@link Graph}, {@link ValueGraph}, and
 * {@link Network}.
 *
 * @author Joshua O'Madadhain
 * @param <N> Node parameter type
 */
interface ArchetypeGraph<N> extends SuccessorsFunction<N>, PredecessorsFunction<N> {
  //
  // Graph-level accessors
  //

  /** Returns all nodes in this graph, in the order specified by {@link #nodeOrder()}. */
  Set<N> nodes();

  //

// @Ignore affects the Android test runner, which respects JUnit 4 annotations on JUnit 3 tests.
@SuppressWarnings("JUnit4ClassUsedInJUnit3")
public abstract class AbstractMultisetSetCountTester<E> extends AbstractMultisetTester<E> {
  /*
   * TODO: consider adding MultisetFeatures.SUPPORTS_SET_COUNT. Currently we
   * assume that using setCount() to increase the count is permitted iff add()

import static org.apache.maven.cling.invoker.CliUtils.toPlexusLoggingLevel;

/**
 * Container capsule backed by Plexus Container.
 *
 * @param <C> The context type.
 */
public class PlexusContainerCapsuleFactory<C extends LookupContext> implements ContainerCapsuleFactory<C> {
    @Override
    public ContainerCapsule createContainerCapsule(