assertTrue("Should contain line 9999", result.getContent().contains("Line 9999"));
    }

    /**
     * Test extraction with various Unicode characters.
     */
    public void test_getText_unicodeContent_extractsCorrectly() {
        final String unicodeContent = "Hello 世界 مرحبا мир שלום";

Disallow: /test/

# Case 9: Special characters in paths
User-agent: SpecialCharBot
Disallow: /path with spaces/
Disallow: /path%20encoded/
Disallow: /path?query=value
Disallow: /path#fragment
Allow: /unicode/日本語/

# Case 10: Multiple User-agents in sequence
User-agent: Bot1
User-agent: Bot2
User-agent: Bot3
Disallow: /shared/

# Case 11: Sitemap with various formats
Sitemap: http://example.com/sitemap.xml

- Improved error messages with encoding
- Various encoding support
- Edge cases (empty, large, Unicode)
- Special characters handling

**Test Count**: 12 tests

**Key Scenarios**:
- ✅ Default UTF-8 encoding extraction
- ✅ Custom encoding support
- ✅ Error messages include encoding information
- ✅ Large content handling
- ✅ Unicode and special characters
- ✅ Empty and whitespace-only content

---

import org.apache.http.conn.DnsResolver;

/**
 * The {@code IdnDnsResolver} class implements the {@code DnsResolver} interface
 * to provide DNS resolution with support for Internationalized Domain Names (IDN).
 * It converts Unicode domain names to ASCII Compatible Encoding (ACE) using the
 * {@link java.net.IDN} class.
 *
 * <p>This class allows setting a custom flag for the IDN conversion and a custom
 * encoding for URL decoding.</p>
 *

        assertFalse(CharUtil.isUrlChar('\u00A0')); // non-breaking space
        assertFalse(CharUtil.isUrlChar('\u00FF')); // ÿ
    }

    public void test_isUrlChar_unicode() {
        // Test Unicode characters (not valid URL chars without encoding)
        assertFalse(CharUtil.isUrlChar('\u3042')); // あ (Hiragana)
        assertFalse(CharUtil.isUrlChar('\u4E00')); // 一 (CJK)

**Technology Stack:**
- Java 21+, Maven
- OpenSearch (provided dependency)
- Apache Lucene (query parsing, text analysis)
- ICU4J (Unicode text processing)
- JUnit 4 (testing)

**Repository:** https://github.com/codelibs/fess-suggest

---

## Architecture

### Package Structure

```
org.codelibs.fess.suggest/

        // Body with unicode characters
        String unicodeBody = "{\"message\":\"こんにちは世界\"}";
        request.body(unicodeBody);

        assertEquals(unicodeBody, request.body());
    }

    @Test
    public void testParamWithUnicodeCharacters() {
        CurlRequest request = new CurlRequest(Method.GET, "https://example.com");

        // Param with unicode characters

- Restart Fess application

### Translations not showing

- Clear browser cache
- Force language with `?browser_lang=[locale]` parameter
- Check property file encoding (should be UTF-8 or use Unicode escapes `\uXXXX`)
- Verify property keys match exactly with base English files

### Build errors after regeneration

- Check property file syntax (no unescaped special characters)

        try {
            robotsTxt = robotsTxtHelper.parse(in, "UTF-8");
        } finally {
            CloseableUtil.closeQuietly(in);
        }

        // Should handle unicode content
        assertNotNull(robotsTxt);
        assertFalse(robotsTxt.allows("/test/", "TestBot"));
    }

        assertEquals(expected, id); // Should not be truncated
    }

    @Test
    public void testCreateSuggestTextIdWithUnicodeCharacters() {
        // Test with various Unicode characters that may encode differently
        String unicodeText = "日本語テスト🎌🗾こんにちは世界";
        String id = SuggestUtil.createSuggestTextId(unicodeText);
        assertNotNull(id);
        assertTrue(id.length() <= 445);
    }