}

    /**
     * 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" >

    }

    @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() {

        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 |

### Protocols

HTTP/HTTPS, File, FTP/FTPS, SMB/CIFS (SMB1/SMB2+), Storage (MinIO via `storage://`), S3 (`s3://`), GCS (`gcs://`)

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ, LHA), HTML, XML, JSON, Markdown, Media metadata, Images (EXIF/IPTC/XMP), Email (EML)

---

## Architecture

### Module Structure

```
fess-crawler-parent/

			<artifactId>tika-parser-ocr-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-pdf-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-pkg-module</artifactId>
			<version>${tika.version}</version>

        assertTrue(fessConfig.isExtensionAllowed("jpeg"));
        assertTrue(fessConfig.isExtensionAllowed("gif"));
        assertTrue(fessConfig.isExtensionAllowed("png"));
        assertFalse(fessConfig.isExtensionAllowed("pdf"));
        assertFalse(fessConfig.isExtensionAllowed("doc"));
    }

    // Test available extensions
    @Test
    public void test_getAvailableExtensions() {