/**
 * 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;
        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");

        }

        // 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

 * </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();

        // 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() {

        URL url = new URL("gcs://mybucket/dir1/dir2/file.pdf");
        Handler handler = new Handler();
        URLConnection conn = handler.openConnection(url);

        Handler.GcsURLConnection gcsConn = (Handler.GcsURLConnection) conn;

        assertEquals("mybucket", getField(gcsConn, "bucketName"));
        assertEquals("dir1/dir2/file.pdf", getField(gcsConn, "objectName"));
    }

    /**

    void fakeImplementation_happyPath() {
        // Arrange
        FileEntry e = new TestFileEntry("doc.pdf", 2, 0x10, 10L, 20L, 30L, 4096L, 3);

        // Act & Assert: getters return exactly what was provided
        assertAll(() -> assertEquals("doc.pdf", e.getName()), () -> assertEquals(2, e.getType()),
                () -> assertEquals(0x10, e.getAttributes()), () -> assertEquals(10L, e.createTime()),