flink-table/flink-table-common/src/main/java/org/apache/flink/table/data/binary/StringUtf8Utils.java [51:117]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
	public static int encodeUTF8(String str, byte[] bytes) {
		int offset = 0;
		int len = str.length();
		int sl = offset + len;
		int dp = 0;
		int dlASCII = dp + Math.min(len, bytes.length);

		// ASCII only optimized loop
		while (dp < dlASCII && str.charAt(offset) < '\u0080') {
			bytes[dp++] = (byte) str.charAt(offset++);
		}

		while (offset < sl) {
			char c = str.charAt(offset++);
			if (c < 0x80) {
				// Have at most seven bits
				bytes[dp++] = (byte) c;
			} else if (c < 0x800) {
				// 2 bytes, 11 bits
				bytes[dp++] = (byte) (0xc0 | (c >> 6));
				bytes[dp++] = (byte) (0x80 | (c & 0x3f));
			} else if (Character.isSurrogate(c)) {
				final int uc;
				int ip = offset - 1;
				if (Character.isHighSurrogate(c)) {
					if (sl - ip < 2) {
						uc = -1;
					} else {
						char d = str.charAt(ip + 1);
						if (Character.isLowSurrogate(d)) {
							uc = Character.toCodePoint(c, d);
						} else {
							// for some illegal character
							// the jdk will ignore the origin character and cast it to '?'
							// this acts the same with jdk
							return defaultEncodeUTF8(str, bytes);
						}
					}
				} else {
					if (Character.isLowSurrogate(c)) {
						// for some illegal character
						// the jdk will ignore the origin character and cast it to '?'
						// this acts the same with jdk
						return defaultEncodeUTF8(str, bytes);
					} else {
						uc = c;
					}
				}

				if (uc < 0) {
					bytes[dp++] = (byte) '?';
				} else {
					bytes[dp++] = (byte) (0xf0 | ((uc >> 18)));
					bytes[dp++] = (byte) (0x80 | ((uc >> 12) & 0x3f));
					bytes[dp++] = (byte) (0x80 | ((uc >> 6) & 0x3f));
					bytes[dp++] = (byte) (0x80 | (uc & 0x3f));
					offset++; // 2 chars
				}
			} else {
				// 3 bytes, 16 bits
				bytes[dp++] = (byte) (0xe0 | ((c >> 12)));
				bytes[dp++] = (byte) (0x80 | ((c >> 6) & 0x3f));
				bytes[dp++] = (byte) (0x80 | (c & 0x3f));
			}
		}
		return dp;
	}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



flink-table/flink-table-runtime-blink/src/main/java/org/apache/flink/table/runtime/util/StringUtf8Utils.java [48:114]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
	public static int encodeUTF8(String str, byte[] bytes) {
		int offset = 0;
		int len = str.length();
		int sl = offset + len;
		int dp = 0;
		int dlASCII = dp + Math.min(len, bytes.length);

		// ASCII only optimized loop
		while (dp < dlASCII && str.charAt(offset) < '\u0080') {
			bytes[dp++] = (byte) str.charAt(offset++);
		}

		while (offset < sl) {
			char c = str.charAt(offset++);
			if (c < 0x80) {
				// Have at most seven bits
				bytes[dp++] = (byte) c;
			} else if (c < 0x800) {
				// 2 bytes, 11 bits
				bytes[dp++] = (byte) (0xc0 | (c >> 6));
				bytes[dp++] = (byte) (0x80 | (c & 0x3f));
			} else if (Character.isSurrogate(c)) {
				final int uc;
				int ip = offset - 1;
				if (Character.isHighSurrogate(c)) {
					if (sl - ip < 2) {
						uc = -1;
					} else {
						char d = str.charAt(ip + 1);
						if (Character.isLowSurrogate(d)) {
							uc = Character.toCodePoint(c, d);
						} else {
							// for some illegal character
							// the jdk will ignore the origin character and cast it to '?'
							// this acts the same with jdk
							return defaultEncodeUTF8(str, bytes);
						}
					}
				} else {
					if (Character.isLowSurrogate(c)) {
						// for some illegal character
						// the jdk will ignore the origin character and cast it to '?'
						// this acts the same with jdk
						return defaultEncodeUTF8(str, bytes);
					} else {
						uc = c;
					}
				}

				if (uc < 0) {
					bytes[dp++] = (byte) '?';
				} else {
					bytes[dp++] = (byte) (0xf0 | ((uc >> 18)));
					bytes[dp++] = (byte) (0x80 | ((uc >> 12) & 0x3f));
					bytes[dp++] = (byte) (0x80 | ((uc >> 6) & 0x3f));
					bytes[dp++] = (byte) (0x80 | (uc & 0x3f));
					offset++; // 2 chars
				}
			} else {
				// 3 bytes, 16 bits
				bytes[dp++] = (byte) (0xe0 | ((c >> 12)));
				bytes[dp++] = (byte) (0x80 | ((c >> 6) & 0x3f));
				bytes[dp++] = (byte) (0x80 | (c & 0x3f));
			}
		}
		return dp;
	}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -