import java.util.regex.Pattern;

import org.apache.commons.io.ByteOrderMark;
import org.apache.commons.io.input.BOMInputStream;
import org.apache.commons.text.translate.AggregateTranslator;
import org.apache.commons.text.translate.CharSequenceTranslator;
import org.apache.commons.text.translate.EntityArrays;
import org.apache.commons.text.translate.LookupTranslator;
import org.apache.commons.text.translate.NumericEntityUnescaper;

 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>
 *   <li>Reading content as plain text if all other methods fail</li>
 *   <li>Applying post-extraction filters</li>
 *   <li>Handling Tika exceptions, including zip bomb exceptions</li>
 * </ul>
 *
 * <p>
 * The class also supports configuration options such as:
 * </p>

### Key Features

- **Multi-Protocol Support**: HTTP/HTTPS, File System, FTP, SMB/CIFS, Cloud Storage (MinIO, S3)

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/zip/test.zip");
        final String content = zipExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {

import org.codelibs.fess.crawler.util.XmlUtil;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;

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

import jakarta.annotation.Resource;

/**
 * <p>

        this.tempDir = tempDir;
    }

    /**
     * Sets the command to execute for text extraction.
     * @param command The command to set.
     */
    public void setCommand(final String command) {
        this.command = command;
    }

    /**
     * Sets the timeout for command execution.
     * @param executionTimeout The execution timeout in milliseconds.
     */

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

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

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

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

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

     * The pattern captures the charset value specified in the content attribute of the meta tag.
     * Example: <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**

import org.apache.commons.lang3.StringUtils;
import org.apache.commons.net.ftp.FTP;
import org.apache.commons.net.ftp.FTPClient;
import org.apache.commons.net.ftp.FTPClient.NatServerResolverImpl;
import org.apache.commons.net.ftp.FTPClientConfig;
import org.apache.commons.net.ftp.FTPFile;
import org.apache.commons.net.ftp.FTPFileFilters;
import org.apache.commons.net.ftp.FTPSClient;