## Supported Protocols and Formats

### Protocols
- **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
- **File System**: Local and network file system access
- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)

        // Create new filter without initialization
        UrlFilter newFilter = container.getComponent("urlFilter");

        // Clear should work even without initialization
        newFilter.clear();
        assertNotNull(newFilter);
    }

    /**
     * Test adding patterns before initialization
     */
    public void test_addPatterns_beforeInit() {
        // Create new filter

        runner.ensureYellow();
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Before
    public void before() throws Exception {
        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();

import org.codelibs.core.lang.ThreadUtil;

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */

import java.util.List;

import org.codelibs.fess.suggest.Suggester;
import org.codelibs.fess.suggest.settings.SuggestSettings;
import org.codelibs.opensearch.runner.OpenSearchRunner;
import org.junit.AfterClass;
import org.junit.Before;
import org.junit.BeforeClass;
import org.junit.Test;
import org.opensearch.action.admin.indices.create.CreateIndexResponse;
import org.opensearch.common.settings.Settings;

        runner.ensureYellow();
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Before
    public void before() throws Exception {
        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();

        runner.ensureYellow();
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Before
    public void before() throws Exception {
        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();

import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;

import org.junit.Before;
import org.junit.Test;

public class ReadingConverterTest {

    private ReadingConverter converter;
    private TestReadingConverter testConverter;

    @Before
    public void setUp() {
        testConverter = new TestReadingConverter();
        converter = testConverter;
    }

        runner.ensureYellow();
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Before
    public void before() throws Exception {
        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();

        runner.ensureYellow();
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Before
    public void before() throws Exception {
        try {
            runner.admin().indices().prepareDelete("_all").execute().actionGet();
        } catch (IndexNotFoundException ignore) {

        }
        runner.refresh();