LevelDB : Int编解码

1.Encode

1.1 FixedInt编码

参考这篇博客

1.1.1 Fixedint32

代码

void EncodeFixed32(char* buf, uint32_t value) {
  if (port::kLittleEndian) { // 如果是小端序，直接在内存中拷贝过来即可
    memcpy(buf, &value, sizeof(value));
  } else { // 如果是大端序，让其在内存中的排布满足小端序
    buf[0] = value & 0xff;
    buf[1] = (value >> 8) & 0xff;
    buf[2] = (value >> 16) & 0xff;
    buf[3] = (value >> 24) & 0xff;
  }
}

1.1.2 Fixedint64

代码

void EncodeFixed64(char* buf, uint64_t value) {
  if (port::kLittleEndian) {
    memcpy(buf, &value, sizeof(value));
  } else {
    buf[0] = value & 0xff;
    buf[1] = (value >> 8) & 0xff;
    buf[2] = (value >> 16) & 0xff;
    buf[3] = (value >> 24) & 0xff;
    buf[4] = (value >> 32) & 0xff;
    buf[5] = (value >> 40) & 0xff;
    buf[6] = (value >> 48) & 0xff;
    buf[7] = (value >> 56) & 0xff;
  }
}

1.2 Varint编码

查看int32\64最多需要多少字节编码
计算公式：
$x\ast 8-x>32$
解得$x=5$
$y\ast 8-y>64$
解得$y=10$

所以
32位需要5字节
64为需要10字节
原理参考这篇博客

1.2.1 Varint32

以下是编码Varint32的代码

char* EncodeVarint32(char* dst, uint32_t v) {
  // Operate on characters as unsigneds
  unsigned char* ptr = reinterpret_cast<unsigned char*>(dst);
  static const int B = 128;
  if (v < (1<<7)) {
    *(ptr++) = v;
  } else if (v < (1<<14)) {
    *(ptr++) = v | B;
    *(ptr++) = v>>7;
  } else if (v < (1<<21)) {
    *(ptr++) = v | B;
    *(ptr++) = (v>>7) | B;
    *(ptr++) = v>>14;
  } else if (v < (1<<28)) {
    *(ptr++) = v | B;
    *(ptr++) = (v>>7) | B;
    *(ptr++) = (v>>14) | B;
    *(ptr++) = v>>21;
  } else {
    *(ptr++) = v | B;
    *(ptr++) = (v>>7) | B;
    *(ptr++) = (v>>14) | B;
    *(ptr++) = (v>>21) | B;
    *(ptr++) = v>>28;
  }
  return reinterpret_cast<char*>(ptr);
}

1.2.2 Varint64

// 写法为什么和Varint32不一致，答：大牛为了让我们看懂32的，64如果也这么写太长了。
char* EncodeVarint64(char* dst, uint64_t v) {
  static const int B = 128;
  unsigned char* ptr = reinterpret_cast<unsigned char*>(dst);
  while (v >= B) {
    *(ptr++) = (v & (B-1)) | B;
    v >>= 7;
  }
  *(ptr++) = static_cast<unsigned char>(v);
  return reinterpret_cast<char*>(ptr);
}

2.Decode

2.1 Fixedint解码

2.1.1 Fixedint32解码

inline uint32_t DecodeFixed32(const char* ptr) {
  if (port::kLittleEndian) {
    // Load the raw bytes
    uint32_t result;
    memcpy(&result, ptr, sizeof(result));  // gcc optimizes this to a plain load
    return result;
  } else {
    return ((static_cast<uint32_t>(static_cast<unsigned char>(ptr[0])))
        | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[1])) << 8)
        | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[2])) << 16)
        | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[3])) << 24));
  }
}

2.1.2 Fixedint64解码

inline uint64_t DecodeFixed64(const char* ptr) {
  if (port::kLittleEndian) {
    // Load the raw bytes
    uint64_t result;
    memcpy(&result, ptr, sizeof(result));  // gcc optimizes this to a plain load
    return result;
  } else {
    uint64_t lo = DecodeFixed32(ptr);
    uint64_t hi = DecodeFixed32(ptr + 4);
    return (hi << 32) | lo;
  }
}

2.2 Varint解码

2.2.1 Varint32解码

inline const char* GetVarint32Ptr(const char* p,
                                  const char* limit,
                                  uint32_t* value) {
  if (p < limit) {
    uint32_t result = *(reinterpret_cast<const unsigned char*>(p));
    if ((result & 128) == 0) {
      *value = result;
      return p + 1;
    }
  }
  return GetVarint32PtrFallback(p, limit, value);
}

const char* GetVarint32PtrFallback(const char* p,
                                   const char* limit,
                                   uint32_t* value) {
  uint32_t result = 0;
  for (uint32_t shift = 0; shift <= 28 && p < limit; shift += 7) {
    uint32_t byte = *(reinterpret_cast<const unsigned char*>(p));
    p++;
    if (byte & 128) {
      // More bytes are present
      result |= ((byte & 127) << shift);
    } else {
      result |= (byte << shift);
      *value = result;
      return reinterpret_cast<const char*>(p);
    }
  }
  return nullptr;
}

2.2.2 Varint64解码

const char* GetVarint64Ptr(const char* p, const char* limit, uint64_t* value) {
  uint64_t result = 0;
  for (uint32_t shift = 0; shift <= 63 && p < limit; shift += 7) {
    uint64_t byte = *(reinterpret_cast<const unsigned char*>(p));
    p++;
    if (byte & 128) {
      // More bytes are present
      result |= ((byte & 127) << shift);
    } else {
      result |= (byte << shift);
      *value = result;
      return reinterpret_cast<const char*>(p);
    }
  }
  return nullptr;
}