protobuf教程(二)---核心编码原理

0000 0001

1010 1100 0000 0010

const maxVarintBytes = 10 // maximum length of a varint

// 返回Varint类型编码后的字节流
func EncodeVarint(x uint64) []byte {
	var buf [maxVarintBytes]byte
	var n int
	// 下面的编码规则需要详细理解:
	// 1.每个字节的最高位是保留位, 如果是1说明后面的字节还是属于当前数据的,如果是0,那么这是当前数据的最后一个字节数据
	//  看下面代码,因为一个字节最高位是保留位,那么这个字节中只有下面7bits可以保存数据
	//  所以,如果x>127,那么说明这个数据还需大于一个字节保存,所以当前字节最高位是1,看下面的buf[n] = 0x80 | ...
	//  0x80说明将这个字节最高位置为1, 后面的x&0x7F是取得x的低7位数据, 那么0x80 | uint8(x&0x7F)整体的意思就是
	//  这个字节最高位是1表示这不是最后一个字节,后面7为是正式数据! 注意操作下一个字节之前需要将x>>=7
	// 2.看如果x<=127那么说明x现在使用7bits可以表示了,那么最高位没有必要是1,直接是0就ok!所以最后直接是buf[n] = uint8(x)
	//
	// 如果数据大于一个字节(127是一个字节最大数据), 那么继续, 即: 需要在最高位加上1
	for n = 0; x > 127; n++ {
	    // x&0x7F表示取出下7bit数据, 0x80表示在最高位加上1
		buf[n] = 0x80 | uint8(x&0x7F)
		// 右移7位, 继续后面的数据处理
		x >>= 7
	}
	// 最后一个字节数据
	buf[n] = uint8(x)
	n++
	return buf[0:n]
}

func DecodeVarint(buf []byte) (x uint64, n int) {
	for shift := uint(0); shift < 64; shift += 7 {
		if n >= len(buf) {
			return 0, 0
		}
		b := uint64(buf[n])
		n++
    // 下面这个分成三步走:
		// 1: b & 0x7F 获取下7bits有效数据
		// 2: (b & 0x7F) << shift 由于是小端序, 所以每次处理一个Byte数据, 都需要向高位移动7bits
		// 3: 将数据x和当前的这个字节数据 | 在一起
		x |= (b & 0x7F) << shift
		if (b & 0x80) == 0 {
			return x, n
		}
	}

	// The number is too large to represent in a 64-bit value.
	return 0, 0
}

Zigzag(n) = (n << 1) ^ (n >> 31), n 为 sint32 时

Zigzag(n) = (n << 1) ^ (n >> 63), n 为 sint64 时

  /**
   * Encode a ZigZag-encoded 32-bit value.  ZigZag encodes signed integers
   * into values that can be efficiently encoded with varint.  (Otherwise,
   * negative values must be sign-extended to 64 bits to be varint encoded,
   * thus always taking 10 bytes on the wire.)
   *
   * @param n A signed 32-bit integer.
   * @return An unsigned 32-bit integer, stored in a signed int because
   *         Java has no explicit unsigned support.
   */
  public static int encodeZigZag32(final int n) {
    // Note:  the right-shift must be arithmetic
    return (n << 1) ^ (n >> 31);
  }

  /**
   * Encode a ZigZag-encoded 64-bit value.  ZigZag encodes signed integers
   * into values that can be efficiently encoded with varint.  (Otherwise,
   * negative values must be sign-extended to 64 bits to be varint encoded,
   * thus always taking 10 bytes on the wire.)
   *
   * @param n A signed 64-bit integer.
   * @return An unsigned 64-bit integer, stored in a signed int because
   *         Java has no explicit unsigned support.
   */
  public static long encodeZigZag64(final long n) {
    // Note:  the right-shift must be arithmetic
    return (n << 1) ^ (n >> 63);
  }

/**
   * Decode a ZigZag-encoded 32-bit value. ZigZag encodes signed integers into values that can be
   * efficiently encoded with varint. (Otherwise, negative values must be sign-extended to 64 bits
   * to be varint encoded, thus always taking 10 bytes on the wire.)
   *
   * @param n An unsigned 32-bit integer, stored in a signed int because Java has no explicit
   *     unsigned support.
   * @return A signed 32-bit integer.
   */
  public static int decodeZigZag32(final int n) {
    return (n >>> 1) ^ -(n & 1);
  }

  /**
   * Decode a ZigZag-encoded 64-bit value. ZigZag encodes signed integers into values that can be
   * efficiently encoded with varint. (Otherwise, negative values must be sign-extended to 64 bits
   * to be varint encoded, thus always taking 10 bytes on the wire.)
   *
   * @param n An unsigned 64-bit integer, stored in a signed int because Java has no explicit
   *     unsigned support.
   * @return A signed 64-bit integer.
   */
  public static long decodeZigZag64(final long n) {
    return (n >>> 1) ^ -(n & 1);
  }

(field_number << 3)|wire_type

message Test {
  required int32 a = 1;
}

message Test2 {
  optional string b = 2;
}

12 07 74 65 73 74 69 6e 67

message Test3 {
  optional Test1 c = 3;
}

1a 03 08 96 01

message Test4 {
  repeated int32 d = 4 [packed=true];
}

22 // tag 0010 0010(field number 010 0 = 4, wire type 010 = 2)

06 // payload size (设置的length = 6 bytes)
 
03 // first element (varint 3)
 
8E 02 // second element (varint 270)
 
9E A7 05 // third element (varint 86942)