*/
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;

 */
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;

- 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

#### Media Files

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;

    <_comment>ZLIB Compressed Data Format</_comment>
    <tika:link>http://tools.ietf.org/html/rfc1950</tika:link>
    <magic priority="45">
      <!-- Low/No compression -->
      <match value="\x78\x01" type="string" offset="0" />
      <!-- Medium compression -->
      <match value="\x78\x5e" type="string" offset="0" />
      <!-- Default compression -->

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;

				"application/vnd.motorola.flexsuite.wem",
				"application/vnd.motorola.iprm",
				"application/vnd.mozilla.xul+xml",
				"application/vnd.ms-artgalry",
				"application/vnd.ms-asf",
				"application/vnd.ms-cab-compressed",
				"application/vnd.ms-excel",
				"application/vnd.ms-excel.addin.macroenabled.12",
				"application/vnd.ms-excel.sheet.macroenabled.12",
				"application/vnd.ms-excel.sheet.binary.macroenabled.12",

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,

     */
    public void setReadAsTextIfFailed(final boolean readAsTextIfFailed) {
        this.readAsTextIfFailed = readAsTextIfFailed;
    }

    /**
     * Sets the maximum compression ratio.
     * @param maxCompressionRatio The max compression ratio.
     */
    public void setMaxCompressionRatio(final long maxCompressionRatio) {
        this.maxCompressionRatio = maxCompressionRatio;
    }

    /**