import org.commonmark.node.Node;
import org.commonmark.node.Text;
import org.commonmark.parser.Parser;
import org.commonmark.renderer.text.TextContentRenderer;

/**
 * Extracts text content and metadata from Markdown files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>YAML front matter metadata extraction</li>

    /*
     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getEncodingPattern()
     */
    @Override
    protected Pattern getEncodingPattern() {
        return metaCharsetPattern;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.impl.AbstractXmlExtractor#getTagPattern()
     */
    @Override

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);

                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {
                            final Map<String, String> map = new HashMap<>();
                            map.put(ExtractData.RESOURCE_NAME_KEY, filename);
                            buf.append(extractor.getText(new IgnoreCloseInputStream(ais), map).getContent());

                    final Extractor extractor = extractorFactory.getExtractor(mimeType);
                    if (extractor != null) {
                        try {
                            final Map<String, String> map = new HashMap<>();
                            map.put(ExtractData.RESOURCE_NAME_KEY, filename);
                            buf.append(extractor.getText(new IgnoreCloseInputStream(ais), map).getContent());

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

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

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

 * 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.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */

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

import java.io.InputStream;
import java.util.Map;

import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.
 */

            try {
                httpClient.close();
            } catch (final IOException e) {
                logger.warn("Failed to close HTTP client for API extractor", e);
            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters

import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for archive extractor error handling improvements.
 * Tests partial extraction, error recovery, and improved error messages.
 */