}

        // Test WildcardBot - wildcard patterns
        // Disallow: /*.pdf$ - should block .pdf files but not .pdf with query params
        assertFalse(robotsTxt.allows("/document.pdf", "WildcardBot"));
        assertFalse(robotsTxt.allows("/files/report.pdf", "WildcardBot"));
        assertTrue(robotsTxt.allows("/document.pdf?download=true", "WildcardBot")); // $ means exact end

		<property name="commandList">
			["${path}/generate-thumbnail",
			"pdf",
			"${url}",
			"${outputFile}"]
		</property>
		<property name="generatorList">
			["${path}/generate-thumbnail"]
		</property>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/pdf"
			</arg>
		</postConstruct>
		<postConstruct name="register"></postConstruct>
	</component>

 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {
 *     ExtractData extractData = new ExtractorBuilder(crawlerContainer, in, new HashMap<>())
 *         .mimeType("application/pdf")
 *         .filename("example.pdf")
 *         .maxContentLength(1024 * 1024)
 *         .extract();
 *
 *     String content = extractData.getContent();

		</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" >

        }
    }

    /**
     * Adds or updates a MIME type to file type mapping.
     *
     * @param mimetype the MIME type to map (e.g., "application/pdf")
     * @param filetype the file type classification (e.g., "pdf")
     */
    public void add(final String mimetype, final String filetype) {
        mimetypeMap.put(mimetype, filetype);
    }

    /**

application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File
application/oda                oda
application/pagemaker          pm5 pt5 pm       # PageMaker
application/pdf                pdf              # Adobe Acrobat
application/postscript         ai eps ps        # Postscript File
application/rtf                rtf              # Rich Text File
application/toolbook           tbk              # Toolbook

        // Presentation Formats
        extensionMap.put("odp", "pdf");
        extensionMap.put("otp", "pdf");
        extensionMap.put("sxi", "pdf");
        extensionMap.put("ppt", "pdf");
        extensionMap.put("pptx", "pdf");
        // Drawing Formats
        extensionMap.put("odg", "svg");
        extensionMap.put("otg", "svg");

        extractorMap.put("pdf", new PdfExtractor());

        String sessionId = "test-session-019";
        urlFilter.init(sessionId);

        urlFilter.addInclude(".*\\.PDF$");

        // Test case sensitivity
        assertFalse(urlFilter.match("https://example.com/document.pdf"));
        assertTrue(urlFilter.match("https://example.com/document.PDF"));
    }

    /**
     * Test very long URL handling
     */
    public void test_veryLongUrl() {

  if [[ -z "${im_cmd}" ]] ; then
    echo "ImageMagick (convert or magick) does not exist."
    exit 1
  fi
  check_command pdftoppm
  check_command unoconv
  tmp_pdf_file=/tmp/thumbnail.$$.pdf
  unoconv -e PageRange=1-1 -o ${tmp_pdf_file} -f pdf "${target_file}"
  if [[ ! -f ${tmp_pdf_file} ]] ; then
    echo "unoconv does not work."
    exit 1
  fi
  tmp_png_prefix=/tmp/thumbnail.png.$$

# Test robots.txt for wildcard (*) and end-of-path ($) support
# Based on RFC 9309 specification

# Test wildcard patterns
User-agent: WildcardBot
Disallow: /*.pdf$
Disallow: /admin/*.php
Disallow: /*/private/
Allow: /public/*.html

# Test end-of-path ($) patterns
User-agent: EndPathBot
Disallow: /fish$
Disallow: /temp$
Allow: /fishing

# Test complex patterns
User-agent: ComplexBot
Disallow: /
Allow: /$