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";

        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

        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);
    }

# Whether to remove duplicate terms in documents.
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

     * The value is, e.g. u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6 <br>
     * comment: Unicode space characters for document parsing.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentSpaceChars();

    /**

        }
    }

    /**
     * Test encode with empty byte array
     *
     * @throws Exception
     */
    public void testEncode_EmptyArray() throws Exception {
        final String result = Base64Util.encode(new byte[0]);
        assertEquals("Empty array should return empty string", "", result);
    }

    /**
     * Test encode with null returns empty string
     *
     * @throws Exception

     * <p>
     * This method uses {@link java.util.Base64.Encoder} for encoding.
     * </p>
     *
     * @param inData
     *            The data to encode
     * @return The encoded data, or an empty string if the input is null or empty
     */
    public static String encode(final byte[] inData) {
        if (ArrayUtil.isEmpty(inData)) {
            return "";
        }
        return Base64.getEncoder().encodeToString(inData);