* It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

    @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

    @Override
    protected void setUp() throws Exception {
        super.setUp();

        final Map<String, String> featureMap = newHashMap();
        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        final Map<String, String> propertyMap = newHashMap();
        final Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");

    }

    public void test_getTika_xml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final Map<String, String> params = new HashMap<String, String>();
        params.put("resourceName", "test_sjis.xml");
        final ExtractData extractData = tikaExtractor.getText(in, params);
        final String content = extractData.getContent();

        super.setUp();
        fileTransformer = new FileTransformer();
        fileTransformer.setName("fileTransformer");
        Map<String, String> featureMap = newHashMap();
        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        fileTransformer.setFeatureMap(featureMap);
        Map<String, String> propertyMap = newHashMap();
        fileTransformer.setPropertyMap(propertyMap);

import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;

import javax.xml.xpath.XPathNodes;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

        assertContentType("application/zip", "extractor/zip/test.zip", "hoge.zip");
        assertContentType("application/x-lharc", "extractor/lha/test.lzh", "hoge.lzh"); // TODO is it correct?

        assertContentType("application/xml", "extractor/test.mm", "hoge.mm");

        assertContentType("message/rfc822", "extractor/eml/sample1.eml", "sample1.eml");

        assertContentType("application/octet-stream", null, "hoge");

import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Stream;

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.io.InputStreamUtil;
import org.codelibs.core.lang.StringUtil;

import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.util.TextUtil;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * <p>
 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats

    @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