}

    /**
     * Get file type icon based on URL or mimetype
     */
    function getFileTypeIcon(url, mimetype) {
        if (mimetype) {
            if (mimetype.indexOf('pdf') !== -1) return 'fa-file-pdf-o';
            if (mimetype.indexOf('word') !== -1 || mimetype.indexOf('document') !== -1) return 'fa-file-word-o';

        assertEquals("filetype:\"pdf\"", getAsQuery(Collections.singletonMap(k, new String[] { "pdf" })));
        assertEquals("filetype:\"doc\"", getAsQuery(Collections.singletonMap(k, new String[] { " doc " })));
        assertEquals("filetype:\"pdf\" filetype:\"doc\"", getAsQuery(Collections.singletonMap(k, new String[] { "pdf", "doc" })));
    }

    @Test

		</postConstruct>
		<postConstruct name="addRule">
			<arg>"mimeType"</arg>
			<!-- Supported MIME type -->
			<arg>
  "(application/xml"
+ "|application/xhtml\+xml"
+ "|application/rdf\+xml"
+ "|application/pdf"
+ "|application/x-freemind"
+ "|text/xml"
+ "|text/xml-external-parsed-entity)"
			</arg>
		</postConstruct>
	</component>

	<component name="fsFileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >

						<option value="html" <c:if test="${as.filetype.contains('html')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_html"
							/></option>
						<option value="pdf" <c:if test="${as.filetype.contains('pdf')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_pdf"
							/></option>
						<option value="word" <c:if test="${as.filetype.contains('word')}">selected</c:if>><la:message

        assertEquals(query, result.getQuery());
    }

    @Test
    public void test_summary_withDocumentUrl() {
        final String documentUrl = "https://example.com/doc.pdf";
        final IntentDetectionResult result = IntentDetectionResult.summary(documentUrl, "summary request");

        assertEquals(ChatIntent.SUMMARY, result.getIntent());

    }

    @Test
    public void test_parseExtraQueries_sameGroupOrJoin() {
        setupViewHelperWithFacetGroups(
                createFacetQueryView("filetype", "HTML", "filetype:HTML", "WORD", "filetype:WORD", "PDF", "filetype:PDF"));
        final MockHttpServletRequest request = new MockHttpServletRequest();
        request.setParameterValues("ex_q", new String[] { "filetype:HTML", "filetype:WORD" });

        assertEquals(128, result.length());
    }

    @Test
    public void test_generateId_urlWithUnicode() {
        String result = crawlingInfoHelper.generateId("file:///home/ユーザー/ドキュメント.pdf");
        assertNotNull(result);
        assertEquals(128, result.length());
    }

    @Test
    public void test_generateId_deterministic() {

  public static final String X_CONTENT_TYPE_OPTIONS = "X-Content-Type-Options";

  /**
   * The HTTP <a
   * href="https://iabtechlab.com/wp-content/uploads/2019/06/VAST_4.2_final_june26.pdf">{@code
   * X-Device-IP}</a> header field name. Header used for VAST requests to provide the IP address of
   * the device on whose behalf the request is being made.
   *
   * @since 31.0
   */

        final String tempPath = "/tmp/source.pdf";
        final String outputPath = "/tmp/thumbnail.jpg";

        final String expandedCommand = testCommand.replace("${url}", tempPath).replace("${outputFile}", outputPath);

        assertEquals("convert /tmp/source.pdf -resize 100x100 /tmp/thumbnail.jpg", expandedCommand);

**Key Capabilities:**
- Full-text search with OpenSearch backend
- Web, file system, and data store crawling
- Multi-format document support (Office, PDF, etc.)
- Admin GUI for configuration
- REST API for programmatic access
- SSO integration (OIDC, SAML, SPNEGO, Entra ID)
- i18n support (20+ languages)

## Tech Stack

| Component | Technology |