import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;

            builder.field(SESSION_ID, sessionId);
        }
        if (ruleId != null) {
            builder.field(RULE_ID, ruleId);
        }
        if (url != null) {
            builder.field(URL, url);
        }
        if (parentUrl != null) {
            builder.field(PARENT_URL, parentUrl);
        }
        if (status != null) {
            builder.field(STATUS, status);
        }

- **Filters**: URL filtering with regex patterns
- **Rules**: Content processing rules and validation

## Building and Testing

### Build Commands

```bash
# Build all modules
mvn clean install

# 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

import java.io.IOException;
import java.io.InputStream;
import java.util.LinkedHashSet;
import java.util.Set;

import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;

                    builder.addSort(sortBuilder);
                }
            }
            if (from != null) {
                builder.setFrom(from);
            }
            if (size != null) {
                builder.setSize(size);
            }
        });
    }

    /**
     * Retrieves a list of documents from the OpenSearch index using a custom search request builder.
     *

            builder.field(SESSION_ID, sessionId);
        }
        if (filterType != null) {
            builder.field(FILTER_TYPE, filterType);
        }
        if (url != null) {
            builder.field(URL, url);
        }
        builder.endObject();
        return builder;
    }

            }
        }

        final CloseableHttpClient closeableHttpClient = httpClientBuilder.setDefaultRequestConfig(requestConfigBuilder.build()).build();
        if (!httpClientPropertyMap.isEmpty()) {
            final BeanDesc beanDesc = BeanDescFactory.getBeanDesc(closeableHttpClient.getClass());

        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();
        suggester = Suggester.builder().build(runner.client(), "SuggesterTest");
        suggester.createIndexIfNothing();
    }

    @Test
    public void test_Read() throws Exception {
        String indexName = "test-index";

import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * {@link ExtractorBuilder} is a builder class for creating and configuring an {@link ExtractData} object.
 * It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,

     *
     * @param builder a {@link Consumer} that accepts an {@link XPathFactory} and configures it.
     * @return a configured instance of {@link XPath}.
     * @throws CrawlerSystemException if an error occurs while creating the {@link XPath} instance.
     */
    public XPath createXPath(final Consumer<XPathFactory> builder) {
        try {