/**
 * 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:

        testFileTypeHelper.setTypes(new String[] { "pdf", "doc" });

        // Add existing file type query
        facetQueryView.addQuery("existing_pdf", "filetype:pdf");
        facetQueryView.addQuery("label1", "filetype:html");

        facetQueryView.init();

        Map<String, String> queryMap = facetQueryView.getQueryMap();

        // Should not duplicate existing pdf query

        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";

    }

    public void test_createTask_withValidParams() {
        // Test task creation with valid parameters
        String path = "/path/to/document.pdf";
        Map<String, Object> docMap = new HashMap<>();
        docMap.put("mimetype", "application/pdf");
        docMap.put("title", "Test Document");

        Tuple3<String, String, String> task = thumbnailGenerator.createTask(path, docMap);
        assertNotNull(task);

                "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");

      |Content-Type: application/pdf; charset=utf-8
      |
      |Jesse’s Resumé
      |--AaB03x--
      |
      """.trimMargin().replace("\n", "\r\n")
    val body =
      MultipartBody
        .Builder("AaB03x")
        .setType(MultipartBody.FORM)
        .addFormDataPart(
          "attachment",
          "resumé.pdf",

        assertEquals("filetype:\"pdf\"", getAsQuery(Collections.singletonMap(k, new String[] { "pdf" })));
        assertEquals("filetype:\"doc\"", getAsQuery(Collections.singletonMap(k, new String[] { " doc " })));
        assertEquals("filetype:\"pdf\" filetype:\"doc\"", getAsQuery(Collections.singletonMap(k, new String[] { "pdf", "doc" })));
    }

    public void test_conditions_sitesearch() {

        // 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() {

 * </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();