assertEquals("こめんと", extractData.getValues("w:Comments")[0]);
        assertEquals("たぐ|さぶたいとる", String.join("|", extractData.getValues("dc:subject")));
        assertEquals("Microsoft Office Word", extractData.getValues("extended-properties:Application")[0]);
        assertEquals("sugaya", extractData.getValues("meta:last-author")[0]);
        assertEquals("太郎", extractData.getValues("dc:creator")[0]);

- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)

        @NullAndEmptySource
        @ValueSource(strings = { "Simple ASCII", "Special chars: !@#$%^&*()", "Unicode: ñöt ascii ℃", "Mixed: ASCII + 中文 + Русский",
                "Emojis: 🎉🌟💻", "Very long string with multiple words and various characters 1234567890" })
        void testGetBytesWithVariousInputs(String input) {
            // When
            byte[] result = Strings.getBytes(input, StandardCharsets.UTF_8);

            // Then

400;\n  line-height: 1.5;\n  text-align: left;\n  text-align: start;\n  text-decoration: none;\n  text-shadow: none;\n  text-transform: none;\n  letter-spacing: normal;\n  word-break: normal;\n  white-space: normal;\n  word-spacing: normal;\n  line-break: auto;\n  font-size: var(--bs-tooltip-font-size);\n  word-wrap: break-word;\n  opacity: 0;\n}\n.tooltip.show {\n  opacity: var(--bs-tooltip-opacity);\n}\n.tooltip .tooltip-arrow {\n  display: block;\n  width: var(--bs-tooltip-arrow-width);\n  height:...

Emoji","Segoe UI Symbol","Noto Color Emoji";font-style:normal;font-weight:400;line-height:1.5;text-align:left;text-align:start;text-decoration:none;text-shadow:none;text-transform:none;letter-spacing:normal;word-break:normal;white-space:normal;word-spacing:normal;line-break:auto;font-size:.875rem;word-wrap:break-word;opacity:0}.tooltip.show{opacity:.9}.tooltip .arrow{position:absolute;display:block;width:.8rem;height:.4rem}.tooltip .arrow::before{position:absolute;content:"";border-color:transparent;border-s...

        @BeforeEach
        void setup() {
            testBlock = new TestServerMessageBlock(mockConfig);
        }

        @Test
        @DisplayName("Test decode with mismatched word count")
        void testDecodeWithMismatchedWordCount() throws SMBProtocolDecodingException {
            TestServerMessageBlock customBlock = new TestServerMessageBlock(mockConfig) {
                @Override

                    appendJson("user-session-id", entity.getUserSessionId(), buf).append(',');
                    appendJson("user", entity.getUser(), buf).append(',');
                    appendJson("search-word", entity.getSearchWord(), buf).append(',');
                    appendJson("hit-count", entity.getHitCount(), buf).append(',');
                    appendJson("query-page-size", entity.getQueryPageSize(), buf).append(',');

        // Test convert with long text
        converter.init();
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 1000; i++) {
            sb.append("word").append(i).append(" ");
        }
        String text = sb.toString();
        String field = "content";

        List<String> readings = converter.convert(text, field, "en");

        assertNotNull(readings);

        // Test empty query
        String[] emptyKeywords = SuggestUtil.parseQuery("", field);
        assertNotNull(emptyKeywords);
        assertEquals(0, emptyKeywords.length);

        // Test single word query
        String[] singleKeyword = SuggestUtil.parseQuery("single", field);
        assertNotNull(singleKeyword);
        assertEquals(1, singleKeyword.length);
        assertEquals("single", singleKeyword[0]);
    }

    <alias type="application/vnd.ms-word"/>
    <_comment>Microsoft Word Document</_comment>
    <tika:link>http://en.wikipedia.org/wiki/.doc</tika:link>
    <tika:uti>com.microsoft.word.doc</tika:uti>
    <magic priority="50">
      <match value="Microsoft\ Word\ 6.0\ Document" type="string" offset="2080"/>
      <match value="Documento\ Microsoft\ Word\ 6" type="string" offset="2080"/>