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

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;
import org.codelibs.core.io.CloseableUtil;

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

				"application/vnd.sun.xml.calc.template",
				"application/vnd.sun.xml.draw",
				"application/vnd.sun.xml.draw.template",
				"application/vnd.sun.xml.impress",
				"application/vnd.sun.xml.impress.template",
				"application/vnd.sun.xml.math",
				"application/vnd.sun.xml.writer",
				"application/vnd.sun.xml.writer.global",
				"application/vnd.sun.xml.writer.template",
				"application/vnd.sun.wadl+xml",

  </mime-type>

  <mime-type type="application/gzip">
    <_comment>Gzip Compressed Archive</_comment>
    <alias type="application/x-gzip"/>
    <alias type="application/x-gunzip"/>
    <alias type="application/gzipped"/>
    <alias type="application/gzip-compressed"/>
    <alias type="application/x-gzip-compressed"/>
    <alias type="gzip/document"/>
    <magic priority="45">

import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,

     * @param clientMap The map of clients.
     */
    @Override
    public void setClientMap(final Map<Pattern, CrawlerClient> clientMap) {
        factory.setClientMap(clientMap);
    }

    /**
     * Compares this wrapper to another object for equality.
     * Equality is determined by the wrapped factory.
     * @param obj The object to compare.
     * @return true if equal, false otherwise.
     */
    @Override

- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data