*/
package org.codelibs.fess.crawler.util;

import java.io.IOException;
import java.io.Reader;
import java.util.HashSet;
import java.util.Set;

import org.apache.commons.lang3.StringUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *

 * </p>
 * <ul>
 *   <li>Namespace awareness</li>
 *   <li>Coalescing</li>
 *   <li>Entity expansion</li>
 *   <li>Ignoring comments and whitespace</li>
 *   <li>Validation</li>
 *   <li>XInclude awareness</li>
 * </ul>
 *
 * <p>

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
import java.util.function.Function;

import org.apache.commons.lang3.RandomUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.ThreadUtil;

				"text/vnd.iptc.anpa",
				"text/vnd.iptc.newsml",
				"text/vnd.iptc.nitf",
				"text/vnd.latex-z",
				"text/vnd.motorola.reflex",
				"text/vnd.ms-mediapackage",
				"text/vnd.net2phone.commcenter.command",
				"text/vnd.si.uricatalogue",
				"text/vnd.sun.j2me.app-descriptor",
				"text/vnd.trolltech.linguist",
				"text/vnd.wap.si",
				"text/vnd.wap.sl",
				"text/vnd.wap.wml",

import java.util.Locale;
import java.util.Map;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;

import javax.net.ssl.SSLContext;

import org.apache.commons.io.output.DeferredFileOutputStream;
import org.apache.commons.lang3.SystemUtils;
import org.apache.http.Header;
import org.apache.http.HttpEntity;
import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;

-->
<!--
  Description: This xml file defines the valid mime types used by Tika.
  The mime type data within this file is based on information from various
  sources like Apache Nutch, Apache HTTP Server, the file(1) command, etc.

  Notes:
   * Tika supports a wider range of match types than Freedesktop does
   * Glob patterns must be unique, if there's a clash assign to the most
     popular format