* 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;

        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");

        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");

import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.

 * 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.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.compressors.CompressorStreamFactory;

    /**
     * Get the extracted data.
     * @param extractor The extractor.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) {
        try {
            return extractor.getText(in, params);
        } catch (final RuntimeException e) {

    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override

        final Extractor extractor = new Extractor() {
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                return null;
            }
        };

        assertNull(extractorFactory.getExtractor("test"));
        extractorFactory.addExtractor("test", extractor);
        assertEquals(extractor, extractorFactory.getExtractor("test"));
    }

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