Method cp

basex-core/src/main/java/org/basex/util/Token.java:220–235

Returns the codepoint of a character at the specified position. Returns a replacement character for invalid values. @param token token @param pos character position @return current character

(final byte[] token, final int pos)

   * @return current character
   */
  public static int cp(final byte[] token, final int pos) {
    // 0xxxxxxx
    final byte b = token[pos];
    if(b >= 0) return b;
    // number of bytes to be read
    final int cl = cl(b);
    if(b < -64 || pos + cl > token.length) return REPLACEMENT;
    // 110xxxxx 10xxxxxx
    if(cl == 2) return (b & 0x1F) << 6 | token[pos + 1] & 0x3F;
    // 1110xxxx 10xxxxxx 10xxxxxx
    if(cl == 3) return (b & 0x0F) << 12 | (token[pos + 1] & 0x3F) << 6 |
      token[pos + 2] & 0x3F;
    // 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
    return (b & 0x07) << 18 | (token[pos + 1] & 0x3F) << 12 |
      (token[pos + 2] & 0x3F) << 6 | token[pos + 3] & 0x3F;
  }

  /**
   * Returns the byte length of a UTF-8 character.