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)

  /**
   * 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 character in this string that is either a control character (like
 * `\u0000` or `\n`) or a non-ASCII character. Returns -1 if this string has no such characters.
 */
internal fun String.indexOfControlOrNonAscii(): Int {
  for (i in 0 until length) {
    val c = this[i]
    if (c <= '\u001f' || c >= '\u007f') {
      return i
    }
  }
  return -1
}

/**
 * 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

    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",
    };

    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",
    };

        if (chars.length >= 2 && Character.isUpperCase(chars[0]) && Character.isUpperCase(chars[1])) {
            return name;
        }
        chars[0] = Character.toLowerCase(chars[0]);
        return new String(chars);
    }

    /**
     * Capitalizes a string according to JavaBeans conventions.
     * Note: If the first two characters are uppercase, the string will not be capitalized.
     * <p>

        }
    }

    /**
     * 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

   *
   * @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,

    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