/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:

        url = "http://test.com/hoge1.pdf";
        resourceName = null;
        params.put(ExtractData.URL, url);
        params.put(ExtractData.RESOURCE_NAME_KEY, resourceName);
        assertNull(pdfExtractor.getPassword(params));

        url = "http://test.com/hoge1.pdf";
        resourceName = "hoge2.pdf";
        params.put(ExtractData.URL, url);

        url = "http://test.com/hoge1.pdf";
        resourceName = null;
        assertNull(tikaExtractor.getPassword(createParams(url, resourceName)));

        url = "http://test.com/hoge1.pdf";
        resourceName = "hoge2.pdf";
        assertNull(tikaExtractor.getPassword(createParams(url, resourceName)));

        url = null;
        resourceName = "hoge2.pdf";

        data.putValue(ExtractData.RESOURCE_NAME_KEY, "test.pdf");
        data.putValue(ExtractData.URL, "https://example.com/test.pdf");
        data.putValues(ExtractData.FILE_PASSWORDS, new String[] { "pass1", "pass2" });

        assertEquals("test.pdf", data.getValues(ExtractData.RESOURCE_NAME_KEY)[0]);
        assertEquals("https://example.com/test.pdf", data.getValues(ExtractData.URL)[0]);

                "hoge.pptx");

        assertContentType("image/jpeg", null, "hoge.jpg");
        assertContentType("image/gif", null, "hoge.gif");

        assertContentType("application/pdf", "extractor/test.pdf", "hoge.pdf");

        assertContentType("application/gzip", "extractor/gz/test.tar.gz", "hoge.tar.gz");
        assertContentType("application/zip", "extractor/zip/test.zip", "hoge.zip");

        final Map<String, String> params = new HashMap<>();
        params.put(ExtractData.RESOURCE_NAME_KEY, "test-document.pdf");

        final ExtractData result = filenameExtractor.getText(in, params);

        assertNotNull(result);
        assertEquals("test-document.pdf", result.getContent());
    }

    /**
     * Test extraction with null parameters map.
     */

        void testCaseInsensitiveExtensions() throws IOException {
            assertEquals("application/pdf", mimeMap.getMimeType("PDF"));
            assertEquals("application/pdf", mimeMap.getMimeType("Pdf"));
            assertEquals("application/pdf", mimeMap.getMimeType("pDf"));
            assertEquals("text/html", mimeMap.getMimeType("HTML"));
            assertEquals("text/html", mimeMap.getMimeType("HtMl"));

        }

        // 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();