#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

## Architecture

### Multi-Module Structure

        extensionMap.put("html", "txt");
        // Spreadsheet Formats
        extensionMap.put("ods", "tsv");
        extensionMap.put("ots", "tsv");
        extensionMap.put("sxc", "tsv");
        extensionMap.put("xls", "tsv");
        extensionMap.put("xlsx", "tsv");
        extensionMap.put("csv", "tsv");
        extensionMap.put("tsv", "tsv");
        // Presentation Formats
        extensionMap.put("odp", "pdf");

/**
 * Constants used in the fess-crawler.
 * This class provides a collection of constant values for HTTP methods, status codes,
 * transformer names, boolean values, character encodings, date/time formats, and XML features.
 * It is designed to avoid the instantiation.
 */
public final class Constants {
    /**
     * The GET method.
     */
    public static final String GET_METHOD = "GET";

    /**

     */
    public void test_processUrl_basic() {
        String sessionId = "test-session-012";
        urlFilter.init(sessionId);

        // Process URL should handle different URL formats
        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");
        urlFilter.processUrl("ftp://files.server.com/documents/");

        assertEquals("500", builder.timeoutSettings.indicesTimeout);
        assertEquals("10000ms", builder.timeoutSettings.clusterTimeout);

        SuggestSettings settings = builder.build(client, "timeout-formats-id");
        assertNotNull(settings);
    }

    @Test
    public void testNullTimeoutValues() {
        // Test setting null timeout values

import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>

    <!-- The is the base QuickTime container -->
    <!-- QuickTime video, and all MP4 formats, are based on it -->
    <acronym>QTFF</acronym>
    <_comment>QuickTime container format</_comment>
  </mime-type>
  <mime-type type="application/mp4">
    <!-- Arbitrary data stored in a MP4 container -->
    <_comment>MP4 container format</_comment>
    <glob pattern="*.mp4s"/>
    <sub-class-of type="application/quicktime" />

 * It contains various attributes such as text, readings, fields, tags, roles, languages, kinds, and frequencies.
 * The class provides methods to manipulate and retrieve these attributes, as well as to convert the item to and from different formats.
 */
public class SuggestItem {

    /**
     * The kind of suggest item.
     */
    public enum Kind {
        /** Document kind. */
        DOCUMENT("document"),
        /** Query kind. */

import org.codelibs.fess.crawler.exception.OpenSearchAccessException;
import org.codelibs.fess.crawler.util.OpenSearchResultList;
import org.joda.time.DateTimeZone;
import org.joda.time.format.DateTimeFormatter;
import org.joda.time.format.ISODateTimeFormat;
import org.opensearch.OpenSearchStatusException;
import org.opensearch.action.DocWriteRequest.OpType;
import org.opensearch.action.DocWriteResponse.Result;

				"application/x-msdownload",
				"application/x-ms-installer",
				"application/x-msdownload;format=pe",
				"application/x-msdownload;format=pe32",
				"application/x-msdownload;format=pe64",
				"application/x-msdownload;format=pe-itanium",
				"application/x-msdownload;format=pe-armLE",
				"application/x-msdownload;format=pe-arm7",
				"application/x-msmediaview",
				"application/x-msmetafile",
				"application/x-msmoney",