<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="logHelper"
		class="org.codelibs.fess.crawler.helper.impl.LogHelperImpl">
	</component>

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="mimeTypeHelper"
		class="org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl" instance="singleton">
	</component>

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="sitemapsHelper" class="org.codelibs.fess.crawler.helper.SitemapsHelper"
		instance="singleton">
	</component>

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<!-- Converts child links to normalize it. -->
	<component name="urlConvertHelper" class="org.codelibs.fess.crawler.helper.UrlConvertHelper">
	</component>

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.rule.impl;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**

    public TextExtractor textExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("textExtractor", TextExtractor.class);
        textExtractor = container.getComponent("textExtractor");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.txt");

    private PdfExtractor pdfExtractorForPdfPassword;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer();
        container.singleton("pdfExtractor", PdfExtractor.class)//
                .singleton("pdfExtractorForPdfPassword", PdfExtractor.class)//
                .singleton("mimeTypeHelper", MimeTypeHelperImpl.class)//

    public TarExtractor tarExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer();
        container.singleton("archiveStreamFactory", ArchiveStreamFactory.class)
                .singleton("compressorStreamFactory", CompressorStreamFactory.class)

            final String content = data.getContent();
            logger.info(content);
            assertTrue(content.contains("Exkursion und Museumsbesuch"));
            assertTrue(content.contains("Fahrt nach Baruth"));
            assertTrue(content.contains("Technische Universität"));
        }
    }

    public void test_getText_null() {
        try {
            emlExtractor.getText(null, null);

});

// Configure content extraction
container.singleton("tikaExtractor", TikaExtractor.class);
container.singleton("extractorFactory", ExtractorFactory.class, factory -> {
    factory.addExtractor("text/html", container.getComponent("tikaExtractor"));
    factory.addExtractor("application/pdf", container.getComponent("tikaExtractor"));
});

Crawler crawler = container.getComponent("crawler");