/**
   * 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

   * Returns the index of the first matching BMP character in a character sequence, or {@code -1} if
   * no matching character is present.
   *
   * <p>The default implementation iterates over the sequence in forward order calling {@link
   * #matches} for each character.
   *
   * @param sequence the character sequence to examine from the beginning
   * @return an index, or {@code -1} if no character matches
   */

 *
 *  * In queries, ' ' is encoded to '+' and '+' is encoded to "%2B".
 *
 *  * Characters in `encodeSet` are percent-encoded.
 *
 *  * Control characters and non-ASCII characters are percent-encoded.
 *
 *  * All other characters are copied without transformation.
 *
 * @param alreadyEncoded true to leave '%' as-is; false to convert it to '%25'.

/**
 * 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

        }
    }

    /**
     * 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

    // 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.
     *

import static com.google.common.truth.Truth.assertThat;
import static java.lang.Character.MAX_CODE_POINT;
import static java.lang.Character.MAX_HIGH_SURROGATE;
import static java.lang.Character.MAX_LOW_SURROGATE;
import static java.lang.Character.MIN_HIGH_SURROGATE;
import static java.lang.Character.MIN_LOW_SURROGATE;
import static java.lang.Character.MIN_SUPPLEMENTARY_CODE_POINT;
import static java.nio.charset.StandardCharsets.UTF_8;

import org.dbflute.optional.OptionalEntity;

/**
 * Character mapping file handler for managing character mapping dictionaries.
 * This class provides functionality to load, parse, and manage character mapping
 * rules that define how input characters should be transformed to output characters
 * during text analysis and search processing.
 *
 * Character mapping files contain mapping rules in the format:
 * input1,input2,... => output

        for (int i = 0; i < testStringTrue.length(); i++) {
            assertEquals(testStringTrue.charAt(i), (char) unicodeStringTrue.buffer[i], "Character mismatch");
        }
        assertEquals(0, unicodeStringTrue.buffer[testStringTrue.length()], "Last character should be zero");

        // Test with a non-empty string and zterm = false
        String testStringFalse = "Hello";

    String[] BAD_STRINGS = {
      String.valueOf(Character.MIN_LOW_SURROGATE),
      Character.MIN_LOW_SURROGATE + "xyz",
      "abc" + Character.MIN_LOW_SURROGATE,
      "abc" + Character.MIN_LOW_SURROGATE + "xyz",
      String.valueOf(Character.MAX_LOW_SURROGATE),
      Character.MAX_LOW_SURROGATE + "xyz",
      "abc" + Character.MAX_LOW_SURROGATE,
      "abc" + Character.MAX_LOW_SURROGATE + "xyz",
    };