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)

}

/**
 * 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

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

/**
 * Servlet filter for handling character encoding conversion and URL redirection.
 * This filter processes requests with specific encoding requirements and converts
 * character encodings according to configured mapping rules.
 *
 * <p>The filter intercepts requests matching configured path patterns and
 * redirects them with proper character encoding applied to parameters.</p>
 */

   * 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
   */