assertTrue(urlFilter.match("http://test.com/a"));

    }

    public void test_match_exclude_case2() {
        urlFilter.addExclude("http://example.com/.*");
        urlFilter.addExclude("http://test.com/.*");

        final String sessionId = "id1";
        urlFilter.init(sessionId);

        assertFalse(urlFilter.match("http://example.com/"));

        super.removeInclude(include);

        // Update the project's SourceRoots
        updateProjectSourceRoot();
    }

    @Override
    public void addExclude(String exclude) {
        // Update the underlying Resource model
        super.addExclude(exclude);

        // Update the project's SourceRoots
        updateProjectSourceRoot();
    }

    @Override
    public void removeExclude(String exclude) {

        // Test empty pattern
        urlFilter.addInclude("");
        urlFilter.addExclude("");

        // Test single character pattern
        urlFilter.addInclude(".");
        urlFilter.addExclude("*");

        // Test patterns with only special characters
        urlFilter.addInclude("^$");
        urlFilter.addExclude(".*");

        // Should handle boundary conditions gracefully

     */
    protected UrlFilterService urlFilterService;

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.filter.UrlFilter#addExclude(java.lang.String)
     */
    @Override
    public void addExclude(final String urlPattern) {
        try {
            Pattern.compile(urlPattern);
        } catch (final Exception e) {
            if (logger.isWarnEnabled()) {

     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *
     * @param url URL
     */

```

### URL Filtering

```java
// Include patterns
crawler.urlFilter.addInclude("https://example.com/.*");
crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols

        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }

     */
    public void addExcludeFilter(final String regexp) {
        if (StringUtil.isNotBlank(regexp)) {
            urlFilter.addExclude(regexp);
        }
    }

    /**
     * Stops the crawling process.
     * Sets the crawler status to DONE and interrupts all crawler threads.
     */
    public void stop() {
        if (logger.isInfoEnabled()) {

3. **Add test with sample file** in `src/test/resources/`

### Configuring URL Filtering

```java
// Include patterns (must match)
crawler.urlFilter.addInclude("https://example.com/.*");

// Exclude patterns (must not match)
crawler.urlFilter.addExclude(".*\\.(css|js|png|jpg)$");
```

### Setting Crawl Limits

```java
context.setMaxAccessCount(1000);  // Max URLs (0 = unlimited)

        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }