* assigned characters, including important CJK characters and emoji.
 *
 * <p>Supplementary characters are <a
 * href="https://docs.oracle.com/javase/8/docs/api/java/lang/Character.html#supplementary">encoded
 * into a {@code String} using surrogate pairs</a>, and a {@code CharMatcher} treats these just as
 * two separate characters. {@link #countIn} counts each supplementary character as 2 {@code char}s.
 *

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)

    // 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.
     *

   *
   * <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

  }

  /**
   * Returns the escaped form of the given character, or {@code null} if this character does not
   * need to be escaped. 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 a one-character array containing the character itself. This enables the escaping algorithm

        }
        return c;
    }

    /**
     * Merges two characters, handling voiced and semi-voiced sound marks.
     * @param c1 The first character.
     * @param c2 The second character.
     * @return The merged character.
     */
    public static char mergeChar(final char c1, final char c2) {
        if (c2 == 'ﾞ') {

        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>

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;

    }

    /**
     * Strips invalid XML characters from the input string.
     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD

  /**
   * 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