*
   * <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

/**
 * 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

     * The name of the access token.
     * This is a required field with a maximum length of 1000 characters.
     */
    @Required
    @Size(max = 1000)
    public String name;

    /**
     * The actual access token string.
     * This is the token value that will be used for authentication.
     * Maximum length is 10000 characters.
     */
    @Size(max = 10000)
    public String token;

    /**

  /**
   * 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

    // 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.
     *

            throw new SmbException("Path contains null bytes");
        }

        // Check for control characters
        if (strictMode && CONTROL_CHARS.matcher(path).find()) {
            log.warn("Path contains control characters: {}", sanitizeForLog(path));
            throw new SmbException("Path contains control characters");
        }

        // Check for traversal sequences
        if (containsTraversal(path)) {

    @ValidateTypeFailure
    public Integer crudMode;

    /** The name of the file configuration (required, maximum 200 characters). */
    @Required
    @Size(max = 200)
    public String name;

    /** The description of the file configuration (maximum 1000 characters). */
    @Size(max = 1000)
    public String description;

    /** The file paths to crawl (required, must be valid file URIs). */

   * generalized escaping for characters.
   *
   * <p>Note that arrays returned by this method must not be modified once they have been returned.
   * However it is acceptable to return the same array multiple times (even for different input
   * characters).
   *
   * @param c the character to escape
   * @return the replacement characters, or {@code null} if no escaping was required
   */

        // Test toString with buffer containing non-printable characters or special unicode
        String unicodeChars = "你好世界"; // "Hello World" in Chinese
        UnicodeString unicodeStringChinese = new UnicodeString(unicodeChars, false);
        assertEquals(unicodeChars, unicodeStringChinese.toString(), "toString should handle unicode characters correctly");

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;