/**
 * Represents a single character mapping rule that defines how input characters are mapped to output characters
 * for text analysis and search processing. This class is used in character mapping dictionaries to transform
 * text during indexing and search operations.
 *
 * <p>Each mapping item consists of one or more input character sequences that are mapped to a single output

   * 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,

        }
    }

    /**
     * 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

    private final Map<Character, String> replacementMap = new HashMap<>();
    private char safeMin = Character.MIN_VALUE;
    private char safeMax = Character.MAX_VALUE;
    private @Nullable String unsafeReplacement = null;

    // The constructor is exposed via the builder() method above.
    private Builder() {}

    /**
     * Sets the safe range of characters for the escaper. Characters in this range that have no

  /**
   * Substitute: A character that may be substituted for a character which is determined to be
   * invalid or in error.
   *
   * @since 8.0
   */
  public static final byte SUB = 26;

  /**
   * Escape: A control character intended to provide code extension (supplementary characters) in
   * general information interchange. The Escape character itself is a prefix affecting the

  // The first character in the safe range.
  private final char safeMin;
  // The last character in the safe range.
  private final char safeMax;

  /**
   * Creates a new ArrayBasedCharEscaper instance with the given replacement map and specified safe
   * range. If {@code safeMax < safeMin} then no characters are considered safe.
   *

    // 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.
     *

  /**
   * Asserts that an escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test
   * @param c the character to test
   */
  public static void assertUnescaped(CharEscaper escaper, char c) {
    Assert.assertNull(computeReplacement(escaper, c));
  }

  /**
   * Asserts that a Unicode escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test

  /**
   * Asserts that an escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test
   * @param c the character to test
   */
  public static void assertUnescaped(CharEscaper escaper, char c) {
    Assert.assertNull(computeReplacement(escaper, c));
  }

  /**
   * Asserts that a Unicode escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test