#### 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

/**
 * 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";

    /**

	k, v, ok = strings.Cut(rec, "=")
	if !ok {
		return "", "", s, ErrHeader
	}

	if !validPAXRecord(k, v) {
		return "", "", s, ErrHeader
	}
	return k, v, rem, nil
}

// formatPAXRecord formats a single PAX record, prefixing it with the
// appropriate length.
func formatPAXRecord(k, v string) (string, error) {
	if !validPAXRecord(k, v) {
		return "", ErrHeader
	}

        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

        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");

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;

 */
package org.codelibs.fess.crawler.entity;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>

     */
    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/");

     * must be less than 2,048 characters.
     */
    private String loc;

    /**
     * The date of last modification of the file. This date should be in W3C
     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *
     * Note that this tag is separate from the If-Modified-Since (304) header

 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */
    protected int preloadSize = 512;

    /**
     * Creates a new SitemapsHelper instance.
     */
    public SitemapsHelper() {
        // Default constructor
    }

    /**