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

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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts the filename from the parameters as the content.
 *

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {

        this.userPrefix = userPrefix;
    }

    /**
     * Extracts role type information from SMB (Server Message Block) response data.
     * Processes both SMB and SMB1 protocols to extract allowed and denied SIDs.
     *
     * @param responseData the response data containing SMB metadata
     * @return a list of role type strings extracted from the SMB permissions
     */

            ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *
     * @param document The document to parse, represented as a map of field names to values.
     * @param fields The fields to extract from the document.
     * @param tagFieldNames The names of the fields that contain tags.

    }

    public void test_contentGetterSetter() {
        // Test content getter/setter
        ExtractData data = new ExtractData();

        String content = "This is extracted content";
        data.setContent(content);
        assertEquals(content, data.getContent());

        String newContent = "New content";
        data.setContent(newContent);

        jsonExtractor.setExtractMetadata(false);
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/json/test.json");
        final ExtractData extractData = jsonExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        // Verify no metadata extracted
        assertNull(extractData.getValues("title"));
        assertNull(extractData.getValues("author"));

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>

        }
        resultData.setEncoding(charsetName);
    }

    /**
     * Normalizes the extracted data, particularly handling title normalization.
     *
     * @param responseData the response data from crawling
     * @param dataMap the data map containing extracted field values
     */
    protected void normalizeData(final ResponseData responseData, final Map<String, Object> dataMap) {

                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
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

            throw new RobotsTxtException("Failed to parse robots.txt.", e);
        }
    }

    /**
     * Extracts the value from a line using the given pattern.
     * @param pattern the pattern to match against
     * @param line the line to extract the value from
     * @return the extracted value, or null if no match
     */
    protected String getValue(final Pattern pattern, final String line) {