(d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed

        try (final ResponseData responseData = storageClient.doGet("storage://fess/file1.txt")) {
            assertEquals("storage://fess/file1.txt", responseData.getUrl());
            assertEquals("text/plain", responseData.getMimeType());
            assertEquals("file1", new String(InputStreamUtil.getBytes(responseData.getResponseBody())));
            assertEquals(5, responseData.getContentLength());

                    PdfExtractor pdfExtractor = container.getComponent("pdfExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/pdf", pdfExtractor);
                });
        pdfExtractor = container.getComponent("pdfExtractor");

 * RegexRule rule = new RegexRule();
 * rule.addRule("url", "https://example.com/.*");
 * rule.addRule("contentType", "text/html");
 * rule.setAllRequired(true); // Both URL and content type must match
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setUrl("https://example.com/page1");
 * responseData.setContentType("text/html");
 *
 * boolean matches = rule.match(responseData); // Returns true
 * }
 * </pre>
 *
 */

 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.

        contentLengthHelper = container.getComponent("contentLengthHelper");
    }

    public void test_getMaxLength() {
        final String mimeType = "text/plain";

        assertEquals(DEFAULT_MAX_LENGTH, contentLengthHelper.getMaxLength(mimeType));
        contentLengthHelper.addMaxLength(mimeType, 1000L);
        assertEquals(1000L, contentLengthHelper.getMaxLength(mimeType));

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

			<artifactId>commons-lang3</artifactId>
			<version>${commons.lang3.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-text</artifactId>
			<version>${commons.text.version}</version>
		</dependency>
		<dependency>
			<groupId>commons-net</groupId>
			<artifactId>commons-net</artifactId>
			<version>${commons.net.version}</version>
		</dependency>

            assertEquals(200, responseData.getHttpStatusCode());
            assertEquals(5, responseData.getContentLength());
            assertEquals(baseUrl + "file1.txt", responseData.getUrl());
            assertEquals("text/plain", responseData.getMimeType());
            assertNull(responseData.getResponseBody());
        }
        try (final ResponseData responseData = smbClient.doHead(baseUrl + "dir1/file2.txt")) {

     */
    @Override
    public synchronized void mark(final int readlimit) {
        fileInputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     * This method delegates to {@link FileInputStream#markSupported()}.
     *