```

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

        try {
            new ContentCache((byte[]) null);
            fail("Expected IllegalArgumentException");
        } catch (IllegalArgumentException e) {
            assertTrue(e.getMessage().contains("data must not be null"));
        }
    }

    @Test
    public void testMemoryBasedCacheDefensiveCopy() throws IOException {
        byte[] data = "Hello, World!".getBytes();
        byte[] originalData = data.clone();

      }

      // If the domain is present, it must domain match. Otherwise we have a host-only cookie.
      val urlHost = url.host
      if (domain == null) {
        domain = urlHost
      } else if (!domainMatch(urlHost, domain)) {
        return null // No domain match? This is either incompetence or malice!
      }

      // If the domain is a suffix of the url host, it must not be a public suffix.

if not errorlevel 1 goto installed
echo Failed installing '%SERVICE_ID%' service
goto:eof

:installed
echo The service '%SERVICE_ID%' has been installed.
goto:eof

:err
echo JAVA_HOME environment variable must be set!
pause
goto:eof

rem ---
rem Function for converting Xm[s|x] values into MB which Commons Daemon accepts
rem ---
:convertxm
set value=%~1
rem extract last char (unit)
set unit=%value:~-1%

    // This is a bit of a hack but lets us do quicker per-character checks in
    // the fast path code. The safe min/max values are very unlikely to extend
    // into the range of surrogate characters, but if they do we must not test
    // any values in that range. To see why, consider the case where:
    // safeMin <= {hi,lo} <= safeMax
    // where {hi,lo} are characters forming a surrogate pair such that:
    // codePointOf(hi, lo) > safeMax

    // are nicer though and will fail-fast.
    checkArgument(
        priority >= Thread.MIN_PRIORITY,
        "Thread priority (%s) must be >= %s",
        priority,
        Thread.MIN_PRIORITY);
    checkArgument(
        priority <= Thread.MAX_PRIORITY,
        "Thread priority (%s) must be <= %s",
        priority,
        Thread.MAX_PRIORITY);
    this.priority = priority;
    return this;
  }

  /**

    assertFailsWith<IllegalArgumentException> {
      OkHttpClient
        .Builder()
        .protocols(protocols as List<Protocol>)
    }.also { expected ->
      assertThat(expected.message).isEqualTo("protocols must not contain null")
    }
  }

  @Test fun spdy3IsRemovedFromProtocols() {
    val protocols =
      mutableListOf(
        Protocol.HTTP_1_1,
        Protocol.SPDY_3,
      )
    val client =

import jcifs.internal.util.SMBUtil;
import jcifs.util.Hexdump;

/**
 * SMB2 Oplock Break notification message. This server-initiated message notifies the client
 * that an opportunistic lock must be broken due to conflicting access from another client.
 *
 * @author mbechler
 *
 */
public class Smb2OplockBreakNotification extends ServerMessageBlock2Response {

    private byte oplockLevel;

import java.util.List;
import java.util.Map.Entry;
import org.junit.Ignore;

/**
 * Testers for {@link ListMultimap#put(Object, Object)}.
 *
 * @author Louis Wasserman
 */
@GwtCompatible
@Ignore("test runners must not instantiate and run this directly, only via suites we build")
// @Ignore affects the Android test runner, which respects JUnit 4 annotations on JUnit 3 tests.
@SuppressWarnings("JUnit4ClassUsedInJUnit3")

import com.google.common.collect.testing.features.MapFeature;
import org.junit.Ignore;

/**
 * Tester for {@link Multimap#containsEntry}.
 *
 * @author Louis Wasserman
 */
@GwtCompatible
@Ignore("test runners must not instantiate and run this directly, only via suites we build")
// @Ignore affects the Android test runner, which respects JUnit 4 annotations on JUnit 3 tests.
@SuppressWarnings("JUnit4ClassUsedInJUnit3")