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 {

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 ZIP archives.
 */
public class ZipExtractor extends AbstractExtractor {

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content and metadata from CSV files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic delimiter detection (comma, tab, semicolon, pipe)</li>
 *   <li>Header row detection and extraction</li>
 *   <li>Column name to data value association</li>

 */
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.
 */

    "name": "jacoco",
    "path": "platforms/jvm/jacoco",
    "unitTests": true,
    "functionalTests": true,
    "crossVersionTests": false
  },
  {
    "name": "java-api-extractor",
    "path": "platforms/core-configuration/java-api-extractor",
    "unitTests": true,
    "functionalTests": false,
    "crossVersionTests": false
  },
  {
    "name": "java-compiler-plugin",

            <option value="$PROJECT_DIR$/platforms/core-configuration/isolated-action-services" />
            <option value="$PROJECT_DIR$/platforms/core-configuration/java-api-extractor" />
            <option value="$PROJECT_DIR$/platforms/core-configuration/kotlin-dsl" />
            <option value="$PROJECT_DIR$/platforms/core-configuration/kotlin-dsl-integ-tests" />

        }
        return value;
    }

    /**
     * Extracts the filename from a URL, handling various protocols and URL decoding.
     * Processes HTTP, HTTPS, file, SMB, and FTP URLs appropriately.
     *
     * @param url the URL to extract filename from
     * @param encoding the character encoding (currently unused in this method)
     * @return the extracted filename, or empty string if none found
     */

            return URI.create(url);
        }
        return null;
    }

    /**
     * Adds a field extraction rule with pruning option.
     *
     * @param name the field name
     * @param xpath the XPath expression for extraction
     * @param isPruned whether the extracted content should be pruned
     */
    public void addFieldRule(final String name, final String xpath, final boolean isPruned) {

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The GCS URL to connect to
         */
        protected GcsURLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;

         * This constructor parses the URL to extract bucket and object names.
         *
         * @param url The S3 URL to connect to
         */
        protected S3URLConnection(final URL url) {
            super(url);
            // Extract bucket name from host
            bucketName = url.getHost() != null ? url.getHost() : StringUtil.EMPTY;