leveldb代码阅读1--encoding

leveldb中大量采用了Varint编码，针对uint32和uint64整数进行无损压缩编码，里面的编码，解码分为Varint和Fixedint两种，具体的操作如下，32位和64位操作类似。

Fixedint 编解码

// 代码里默认为小端系统
void EncodeFixed32(char* buf, uint32_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;
  }
}

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;
  }
}

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));
  }
}

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;
  }
}

Varint 编解码

Varint 中的每个byte的最高位bit有特殊含义，如果该位为1，表示下个byte也表示这个数字，如果该位为0，则表示这个数字结束。 对于小于128的数字，一个字节就可以表示。

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);
}

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) {
    //数字小于128
      *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 NULL;
}

bool GetVarint32(Slice* input, uint32_t* value) {
  const char* p = input->data();
  const char* limit = p + input->size();
  const char* q = GetVarint32Ptr(p, limit, value);
  if (q == NULL) {
    return false;
  } else {
    *input = Slice(q, limit - q);
    return true;
  }
}