## Overview

**Fess Crawler** is a powerful, flexible Java-based web crawling framework designed for enterprise-scale content extraction and processing. Built with a modular architecture, it supports multiple protocols (HTTP/HTTPS, File System, FTP, SMB, Cloud Storage) and provides extensive content extraction capabilities from various document formats.

            if (responseData != null) {
                processedUrls.add(responseData.getUrl());
                state++;
            }

            ResultData resultData = new ResultData();
            resultData.setTransformerName(name);
            resultData.setData(("State: " + state).getBytes());
            return resultData;
        }

        @Override

        testRule.crawlerContainer = container;
    }

    /**
     * Test getRuleId and setRuleId
     */
    public void test_ruleId_getterSetter() {
        // Initial state
        assertNull(testRule.getRuleId());

        // Set rule ID
        testRule.setRuleId("testRule1");
        assertEquals("testRule1", testRule.getRuleId());

        // Change rule ID

        urlFilter.addExclude(".*\\/admin\\/.*");
        urlFilter.addExclude(".*#.*");

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertFalse(urlFilter.match("https://example.com/style.css"));
        assertFalse(urlFilter.match("https://example.com/script.js"));
        assertFalse(urlFilter.match("https://example.com/admin/login"));
        assertFalse(urlFilter.match("https://example.com/page#section"));

        assertNull(transformer.getName());
    }

    /**
     * Test getName and setName with normal values
     */
    public void test_name_getterSetter() {
        // Initial state
        assertNull(testTransformer.getName());

        // Set name
        testTransformer.setName("testTransformer");
        assertEquals("testTransformer", testTransformer.getName());

        // Change name

        assertEquals(Long.MAX_VALUE, crawlerContext.getMaxAccessCount());
    }

    /**
     * Test sitemaps add and remove operations
     */
    public void test_sitemaps() {
        // Initial state
        assertNull(crawlerContext.removeSitemaps());

        // Add sitemaps
        String[] sitemaps = new String[] { "http://example.com/sitemap.xml", "http://test.com/sitemap.xml" };

6. Check license headers: `mvn license:format`
7. Commit changes: `git commit -m 'Add amazing feature'`
8. Push to branch: `git push origin feature/amazing-feature`
9. Open a Pull Request

### Code Style

- Use Eclipse formatter configuration (`src/config/eclipse/formatter/java.xml`)
- Follow existing naming conventions
- Add comprehensive JavaDoc for public APIs
- Write unit and integration tests

## License

        assertNotNull(settings);
        // Verify that the settings object was created with the correct parameters
        // Note: We can't directly verify internal state of SuggestSettings without getters,
        // but we can verify it was created successfully
    }

    @Test
    public void testBuildWithCustomSettings() {
        // Test building with all custom settings

    /**
     * Factory for creating crawler clients.
     */
    @Resource
    protected CrawlerClientFactory clientFactory;

    /**
     * Context object containing crawler state and configuration.
     */
    protected CrawlerContext crawlerContext;

    /**
     * Flag indicating whether the crawler runs in background mode.
     */
    protected boolean background = false;

        case DONE:
            return "Crawler has completed";
        default:
            fail("Unexpected status: " + status);
            return null;
        }
    }

    /**
     * Test state transitions (typical workflow)
     */
    public void test_stateTransitions() {
        // Simulate typical crawler lifecycle
        CrawlerStatus currentStatus = CrawlerStatus.INITIALIZING;