import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * Gets a text from .eml file.
 *

    private TestApiExtractorServer server;

    private ApiExtractor extractor;

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

        server = new TestApiExtractorServer(port);
        server.start();

        extractor = new ApiExtractor();
        extractor.setUrl("http://127.0.0.1:" + port + "/");
        extractor.init();
    }

    @Override

	}

	// if not found, for backward compatibility, extract the namespace from
	// the proxy domain. this is a k8s specific hack and should be enabled
	parts := strings.Split(proxy.DNSDomain, ".")
	if len(parts) > 1 { // k8s will have namespace.<domain>
		return parts[0]
	}

	return ""
}

const (
	serviceNodeSeparator = "~"
)

// ParsePort extracts port number from a valid proxy address

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

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

	sr.ReturnNonDecryptable(true)

	// Debug corrupted streams.
	if false {
		sr.SkipEncrypted(true)
		return sr.DebugStream(os.Stdout)
	}
	extracted := false
	for {
		stream, err := sr.NextStream()
		if err != nil {
			if err == io.EOF {
				if extracted {
					return nil
				}
				return errors.New("no data found on stream")
			}
			if errors.Is(err, estream.ErrNoKey) {
				if stream.Name == "inspect.zip" {

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");

		host = ipAddress
	}
	// Strip off IPv6 zone information.
	if i := strings.Index(host, "%"); i > -1 {
		host = host[:i]
	}
	return net.ParseIP(host) != nil
}

// extractHostPort - extracts host/port from many address formats
// such as, ":9000", "localhost:9000", "http://localhost:9000/"
func extractHostPort(hostAddr string) (string, string, error) {
	var addr, scheme string

	if hostAddr == "" {

        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");

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;