*
   * <ul>
   *   <li>The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain
   *       the same.
   *   <li>The special characters ".", "-", "*", and "_" remain the same.
   *   <li>The space character " " is converted into a plus sign "+".
   *   <li>All other characters are converted into one or more bytes using UTF-8 encoding and each

   * is guaranteed to be in the range {@code 0 <= cp <= Character#MAX_CODE_POINT}.
   *
   * <p>If an empty array is returned, this effectively strips the input character from the
   * resulting text.
   *
   * <p>If the character does not need to be escaped, this method should return {@code null}, rather
   * than an array containing the character representation of the code point. This enables the

   * is guaranteed to be in the range {@code 0 <= cp <= Character#MAX_CODE_POINT}.
   *
   * <p>If an empty array is returned, this effectively strips the input character from the
   * resulting text.
   *
   * <p>If the character does not need to be escaped, this method should return {@code null}, rather
   * than an array containing the character representation of the code point. This enables the

 *
 * <ul>
 *   <li>All specified safe characters remain unchanged.
 *   <li>If {@code plusForSpace} was specified, the space character " " is converted into a plus
 *       sign {@code "+"}.
 *   <li>All other characters are converted into one or more bytes using UTF-8 encoding and each
 *       byte is then represented by the 3-character string "%XX", where "XX" is the two-digit,

   *
   * @param replacementMap a map of characters to their escaped representations
   * @param safeMin the lowest character value in the safe range
   * @param safeMax the highest character value in the safe range
   * @param unsafeReplacement the default replacement for unsafe characters or null if no default
   *     replacement is required
   */
  protected ArrayBasedUnicodeEscaper(
      Map<Character, String> replacementMap,
      int safeMin,

        }
    }

    /**
     * Sets a character as a word character.
     *
     * @param ctype2
     *            The array of character types.
     * @param val
     *            The character code.
     */
    protected static void wordChar(final byte[] ctype2, final int val) {
        ctype2[val] |= CT_ALPHA;
    }

    /**
     * Sets characters as whitespace.
     *
     * @param ctype2

package org.codelibs.fess.crawler.util;

/**
 * Utility class for character-related operations.
 */
public final class CharUtil {
    /**
     * Private constructor to prevent instantiation of this utility class.
     */
    private CharUtil() {
    }

    /**
     * Checks if the given character is a valid URL character.
     *
     * Valid URL characters include:
     * - Lowercase letters (a-z)

    // which means they are treated as pairs of safe characters).
    builder.setSafeRange(Character.MIN_VALUE, '\uFFFD');
    // Unsafe characters are replaced with the Unicode replacement character.
    builder.setUnsafeReplacement("\uFFFD");

    /*
     * Except for \n, \t, and \r, all ASCII control characters are replaced with the Unicode
     * replacement character.
     *

   *
   * <ul>
   *   <li>The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain
   *       the same.
   *   <li>The special characters ".", "-", "*", and "_" remain the same.
   *   <li>The space character " " is converted into a plus sign "+".
   *   <li>All other characters are converted into one or more bytes using UTF-8 encoding and each

  }

  /**
   * Returns the escaped form of the given character, or {@code null} if this character does not
   * need to be escaped. If an empty array is returned, this effectively strips the input character
   * from the resulting text.
   *
   * <p>If the character does not need to be escaped, this method should return {@code null}, rather
   * than a one-character array containing the character itself. This enables the escaping algorithm