<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

      }
      assertSip(msg, EXPECTED[i]);
    }
  }

  // This test data comes from "SipHash: a fast short-input PRF", "Appendix A: Test values".
  // It can be downloaded here: https://131002.net/siphash/siphash.pdf
  public void test15ByteStringFromSipHashPaper() {
    byte[] message =
        new byte[] {
          0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e
        };

      }
      assertSip(msg, EXPECTED[i]);
    }
  }

  // This test data comes from "SipHash: a fast short-input PRF", "Appendix A: Test values".
  // It can be downloaded here: https://131002.net/siphash/siphash.pdf
  public void test15ByteStringFromSipHashPaper() {
    byte[] message =
        new byte[] {
          0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e
        };

 * the License.
 */

/*
 * SipHash-c-d was designed by Jean-Philippe Aumasson and Daniel J. Bernstein and is described in
 * "SipHash: a fast short-input PRF" (available at https://131002.net/siphash/siphash.pdf).
 */

package com.google.common.hash;

import static com.google.common.base.Preconditions.checkArgument;

import com.google.errorprone.annotations.Immutable;
import java.io.Serializable;

						<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

        DataStoreParams paramMap = new DataStoreParams();
        paramMap.put("url_exclude_pattern", ".*\\.pdf$");

        boolean result1 = indexUpdateCallback.isUrlCrawlable(paramMap, "http://example.com/test.html");
        boolean result2 = indexUpdateCallback.isUrlCrawlable(paramMap, "http://example.com/test.pdf");

        assertTrue(result1);
        assertFalse(result2);

    }

    @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" });

**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 |

   * href="ftp://www.3gpp.org/tsg_sa/TSG_SA/TSGS_23/Docs/PDF/SP-040065.pdf#page=10">3GPP TS
   * 26.244</a>.
   *
   * @since 20.0
   */
  public static final MediaType THREE_GPP_VIDEO = createConstant(VIDEO_TYPE, "3gpp");

  /**
   * The 3G2 multimedia container format. For more information, see <a
   * href="http://www.3gpp2.org/Public_html/specs/C.S0050-B_v1.0_070521.pdf#page=16">3GPP2
   * C.S0050-B</a>.
   *

### 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/