// String content = extractData.getContent();
    // CloseableUtil.closeQuietly(in);
    // logger.info(content);
    // assertTrue(content.contains("テスト"));
    // }

    public void test_getTika_html() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();

      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the

 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,

     * @param in the input stream to validate
     * @return true if the stream contains valid sitemap data, false otherwise
     */
    public boolean isValid(final InputStream in) {
        return isValid(in, true);
    }

    /**
     * Checks if the given input stream contains valid sitemap data.
     * @param in the input stream to validate

                    InputStream in = null;
                    try {
                        if (isByteStream) {
                            inputStream.reset();
                            in = inputStream;
                        } else {
                            in = new FileInputStream(tempFile);
                        }
                        postFilter.accept(extractData, in);
                    } finally {

 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**
     * Regular expression pattern to match the charset attribute in the meta tag of HTML documents.
     * The pattern captures the charset value specified in the content attribute of the meta tag.

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

        final String resourceName = params == null ? null : params.get(ExtractData.RESOURCE_NAME_KEY);

        String extension;

 *   <li>secretKey - The secret key for authentication</li>
 *   <li>connectTimeout - Connection timeout in milliseconds (default: 10000)</li>
 *   <li>writeTimeout - Write timeout in milliseconds (default: 10000)</li>
 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>

 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,

 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,