FileUtil.writeBytes(robotTxtFile.getAbsolutePath(), buf.toString().getBytes("UTF-8"));
            robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');

            FileUtil.writeBytes(robotTxtFile.getAbsolutePath(), buf.toString().getBytes("UTF-8"));
            robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');

import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import javax.xml.xpath.XPathEvaluationResult;
import javax.xml.xpath.XPathException;
import javax.xml.xpath.XPathNodes;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

    @Resource
    private FesenClient fesenClient;

    private OpenSearchRunner runner;

    @Override
    protected String prepareConfigFile() {
        return "app.xml";
    }

    @Override
    protected boolean isUseOneTimeContainer() {
        return true;
    }

    @Override
    public void setUp() throws Exception {
        // create runner instance

        String[] sitemaps = robotsTxt.getSitemaps();
        assertEquals(2, sitemaps.length);
        assertEquals("http://www.example.com/sitmap.xml", sitemaps[0]);
        assertEquals("http://www.example.net/sitmap.xml", sitemaps[1]);

    }

    public void testParse_disable() {
        final InputStream in = RobotsTxtHelperTest.class.getResourceAsStream("robots.txt");

 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *
 * <p>
 * The MIME type detection is based on the {@code tika-mimetypes.xml} resource, which is loaded during initialization.
 * </p>
 *
 * <p>
 * Usage:
 * </p>
 * <pre>
 * MimeTypeHelperImpl mimeTypeHelper = new MimeTypeHelperImpl();

    @Resource
    private FileTransformer fileTransformer;

    @Resource
    private CrawlerContainer crawlerContainer;

    @Override
    protected String prepareConfigFile() {
        return "crawler.xml";
    }

    public void test_execute_web() throws Exception {
        final CrawlerWebServer server = new CrawlerWebServer(7070);
        server.start();

        final String url = "http://localhost:7070/";

## Quick Start

### Prerequisites

- Java 21 or higher
- OpenSearch/Elasticsearch cluster (2.x+ recommended)
- Maven 3.8+ for building from source

### Installation

Add the dependency to your `pom.xml`:

```xml
<dependency>
    <groupId>org.codelibs.fess</groupId>
    <artifactId>fess-suggest</artifactId>
    <version>15.2.0-SNAPSHOT</version>
</dependency>
```

### Basic Usage

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>