}

        public XmlReaderRequestBuilder url(URL url) {
            this.url = url;
            return this;
        }

        public XmlReaderRequestBuilder inputStream(InputStream inputStream) {
            this.inputStream = inputStream;
            return this;
        }

        public XmlReaderRequestBuilder reader(Reader reader) {
            this.reader = reader;
            return this;
        }

     */
    protected ExtractData getText(final InputStream inputStream, final Map<String, String> params,
            final BiConsumer<ExtractData, InputStream> postFilter) {
        if (inputStream == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        final File tempFile;
        final boolean isByteStream = inputStream instanceof ByteArrayInputStream;
        if (isByteStream) {

    /**
     * Constructs a new IgnoreCloseInputStream that wraps the specified input stream.
     *
     * @param inputStream the input stream to wrap
     */
    public IgnoreCloseInputStream(final InputStream inputStream) {
        this.inputStream = inputStream;
    }

    /**
     * Overrides the close method to ignore the close operation.
     * The underlying input stream will not be closed.
     *

    }

    public void test_getHtml_empty() {
        final InputStream in = new ByteArrayInputStream("".getBytes());
        final String content = htmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertEquals("", content);
    }

    public void test_getEncoding_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");

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

import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;

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

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

import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
import org.apache.logging.log4j.LogManager;

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

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;

     */
    public SitemapSet parse(final InputStream in) {
        return parse(in, true);
    }

    /**
     * Parses a sitemap from the given input stream.
     * @param in the input stream to parse
     * @param recursive whether to recursively parse compressed files
     * @return the parsed sitemap set
     */
    protected SitemapSet parse(final InputStream in, final boolean recursive) {

        final InputStream in = new ByteArrayInputStream(bytes);

        try {
            sitemapsHelper.parse(in);
            fail();
        } catch (final CrawlingAccessException e) {
            // NOP
        }
    }

    public void test_parseXmlSitemaps_invalid2() {
        final byte[] bytes = "test".getBytes();
        final InputStream in = new ByteArrayInputStream(bytes);

     */
    public TarExtractor() {
        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();