assertEquals(longId.toString(), testRule.getRuleId());

        // Special characters in rule ID
        testRule.setRuleId("rule-id_with.special@chars#123");
        assertEquals("rule-id_with.special@chars#123", testRule.getRuleId());

        // Unicode characters
        testRule.setRuleId("ルール日本語");
        assertEquals("ルール日本語", testRule.getRuleId());

        // Whitespace

        assertEquals(0x0101, actualInfoLevel);
    }

    @Test
    void testWriteParametersWithSpecialCharacters() {
        String specialPath = "test/file with spaces and $pecial #chars!.txt";
        trans2QueryPathInfo = new Trans2QueryPathInformation(config, specialPath, TEST_INFO_LEVEL);

        byte[] buffer = new byte[512];
        int written = trans2QueryPathInfo.writeParametersWireFormat(buffer, 0);

    @CsvSource({ "a.txt", "very_long_filename_with_many_characters_to_test_buffer_handling.docx", "file with spaces.pdf", "文件.txt", // Unicode filename
            "file-with-special-chars!@#$%^&().bin" })
    void testDecodeWithVariousFileNames(String fileName) throws SMBProtocolDecodingException {
        byte[] buffer = createValidNotificationBuffer(fileName, FileNotifyInformation.FILE_ACTION_ADDED);

import com.google.common.collect.testing.google.TestStringListMultimapGenerator;
import com.google.common.collect.testing.google.UnmodifiableCollectionTests;
import com.google.common.primitives.Chars;
import com.google.common.testing.CollectorTester;
import com.google.common.testing.EqualsTester;
import com.google.common.testing.NullPointerTester;
import com.google.common.testing.SerializableTester;

    Iterable<CharSource> cycle = Iterables.cycle(ImmutableList.of(source));
    CharSource concatenated = CharSource.concat(cycle);

    String expected = "abcdabcd";

    // read the first 8 chars manually, since there's no equivalent to ByteSource.slice
    // TODO(cgdecker): Add CharSource.slice?
    StringBuilder builder = new StringBuilder();

import com.google.common.collect.ImmutableMultimap;
import com.google.common.collect.Iterables;
import com.google.common.collect.Multiset;
import com.google.common.collect.Ordering;
import com.google.common.primitives.Chars;
import org.jspecify.annotations.NullUnmarked;
import org.junit.Test;
import org.junit.runner.RunWith;
import org.junit.runners.JUnit4;

@RunWith(JUnit4.class)
@NullUnmarked
public class TraverserTest {

});
```

### Text Processing and JSON
```java
import org.codelibs.core.text.*;

// JSON utilities with proper escaping
String escaped = JsonUtil.escape("Hello \"World\" with special chars");
String unescaped = JsonUtil.unescape(escaped);

// Text tokenization
Tokenizer tokenizer = new Tokenizer("field1,field2,field3", ",");
while (tokenizer.hasMoreTokens()) {
    String token = tokenizer.nextToken();

        // with a len of 0 forever
        if (len <= 0) {
          fail("read called with a len of " + len);
        }
        // read fewer than the max number of chars to read
        // shouldn't be a problem unless the buffer is shrinking each call
        return in.read(cbuf, off, Math.max(len - 1024, 0));
      }
    };
  }

        // with a len of 0 forever
        if (len <= 0) {
          fail("read called with a len of " + len);
        }
        // read fewer than the max number of chars to read
        // shouldn't be a problem unless the buffer is shrinking each call
        return in.read(cbuf, off, Math.max(len - 1024, 0));
      }
    };
  }

crawler.document.duplicate.term.removed=false
# Unicode space characters for document parsing.
crawler.document.space.chars=u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6
# Unicode full stop characters for document parsing.
crawler.document.fullstop.chars=u002eu06d4u2e3cu3002
# Encoding for crawling data.
crawler.crawling.data.encoding=UTF-8