import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.
 * <p>

        System.setProperty("java.version", "11.0.1");

        String[] args = new String[] { "8:-Xmx1g", // Exact Java 8
                "11:-Xmx2g", // Exact Java 11
                "17:-Xmx4g", // Exact Java 17
                "11:-XX:+UseG1GC" // Another exact Java 11
        };

        String[] result = JvmUtil.filterJvmOptions(args);
        assertEquals(2, result.length);

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;

Sebastián Ramírez <******@****.***> 1731896744 +0100

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_entity() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_entity.xml");

Sebastián Ramírez <******@****.***> 1731896744 +0100

	}

	// "x-amz-content-sha256" header value from the extracted result.
	extractedContentSha256 := extractedSignedHeaders.Get("x-amz-content-sha256")
	// "host" header value from the extracted result.
	extractedHost := extractedSignedHeaders.Get("host")
	//  "x-amz-date" header from the extracted result.
	extractedDate := extractedSignedHeaders.Get("x-amz-date")
	// extracted `expect` header.

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

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

Sebastián Ramírez <******@****.***> 1731896744 +0100

Sebastián Ramírez <******@****.***> 1731896744 +0100