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

    public void test_getEncoding_utf16lebom() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/xml/test_utf16lebom.xml");
        final BufferedInputStream bis = new BufferedInputStream(in);

            throw new CrawlingAccessException("No response body.");
        }

        final ResultData resultData = new ResultData();
        resultData.setTransformerName(getName());

        try (BufferedInputStream bis = new BufferedInputStream(responseData.getResponseBody())) {
            resultData.setData(IOUtils.toByteArray(bis));
            resultData.setEncoding(responseData.getCharSet());
            return resultData;

        assertEquals("", content);
    }

    public void test_getEncoding_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlXpathExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

        assertEquals("", content);
    }

    public void test_getEncoding_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {

     * @return true if the stream contains valid sitemap data, false otherwise
     */
    protected boolean isValid(final InputStream in, final boolean recursive) {
        final BufferedInputStream bis = new BufferedInputStream(in);
        bis.mark(preloadSize);

        final byte[] bytes = new byte[preloadSize];
        try {
            if (bis.read(bytes) == -1) {
                return false;
            }

        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            final BufferedInputStream bis = new BufferedInputStream(in);
            final String enc = getEncoding(bis);
            final String content = UNESCAPE_HTML4.translate(new String(InputStreamUtil.getBytes(bis), enc));
            return createExtractData(content);

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

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

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;

 * 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.BufferedInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;

     */
    private void copy(final SmbFile src, final File dest) {
        if (dest.exists() && !dest.canWrite()) {
            return;
        }
        try (BufferedInputStream in = new BufferedInputStream(new SmbFileInputStream(src));
                BufferedOutputStream out = new BufferedOutputStream(new FileOutputStream(dest))) {
            final byte[] buf = new byte[1024];
            int length;

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

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URLEncoder;