zipExtractor.setMaxContentSize(100);
            zipExtractor.getText(in, null);
            fail();
        } catch (MaxLengthExceededException e) {
            // pass
        }
        zipExtractor.setMaxContentSize(-1);
    }

    public void test_getText_null() {
        try {
            zipExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/markdown/test.md");
        final ExtractData extractData = markdownExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        final String content = extractData.getContent();
        logger.info(content);

        // Verify plain text extraction

        ExtractData extractData = jodExtractor.getText(in, null);
        String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            jodExtractor.getText(null, null);
            fail();
        } catch (CrawlerSystemException e) {

        final String content = htmlXpathExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getHtml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");
        final String content = htmlXpathExtractor.getText(in, null).getContent();

        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.
     */

        final ExtractData result = textExtractor.getText(in, null);

        assertNotNull(result);
        assertNotNull(result.getContent());
    }

    /**
     * Test that null input stream throws CrawlerSystemException with correct message.
     */
    public void test_getText_nullInputStream_throwsWithMessage() {
        try {
            textExtractor.getText(null, null);

        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_entity() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_entity.xml");
        final String content = xmlExtractor.getText(in, null).getContent();

        }
    }

    /**
     * Test that validateInputStream is called during getText execution.
     */
    public void test_validateInputStream_calledDuringGetText() {
        final InputStream in = new ByteArrayInputStream("test data".getBytes());

        extractor.getText(in, null);

        assertTrue("validateInputStream should be called", extractor.isValidateCalled());

    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/csv/test.csv");
        final ExtractData extractData = csvExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        final String content = extractData.getContent();
        logger.info(content);

        // Verify header extraction

        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        final ExtractData text = extractor.getText(new FileInputStream(contentFile), params);
        assertEquals(content, text.getContent());
    }

    public void test_getText_withUrl() throws IOException {
        final File scriptFile = createScriptTempFile(3);