LevelDB源码分析2-整数编解码

文件coding.cc和coding.h。leveldb有自己的编解码系统。

变长整数编码

每一个Byte最高位bit用0/1表示该整数是否结束，用剩余7bit表示实际的数值。

这四个函数是把value插入到dst最后面

extern void PutFixed32(std::string* dst, uint32_t value);extern void PutFixed64(std::string* dst, uint64_t value);extern void PutVarint32(std::string* dst, uint32_t value);extern void PutVarint64(std::string* dst, uint64_t value);extern void PutLengthPrefixedSlice(std::string* dst, const Slice& value);

先看看如何编码

//对32位整数编码，编码为4字节的整数，小端顺序void EncodeFixed32(char* buf, uint32_t value) {#if __BYTE_ORDER == __LITTLE_ENDIAN  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;#endif}void EncodeFixed64(char* buf, uint64_t value) {#if __BYTE_ORDER == __LITTLE_ENDIAN  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;#endif}

以下是变长整数的编码

//有效位是7位，直接把v按照7bit分割//功能：把unit32位的数字v放入到char* dst中//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;//128 = 2^7 = (1000 0000)2 最高位为1，表示没有完  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;           //一次取7位加上结束位，后面类似，只是把v的低7位移除    *(ptr++) = (v>>7) | B;    *(ptr++) = (v>>14) | B;    *(ptr++) = (v>>21) | B;    *(ptr++) = v>>28;           //最后一位(小端模式),最高位为0，表示已经结束  }  return reinterpret_cast<char*>(ptr);}void PutVarint32(std::string* dst, uint32_t v) {  char buf[5];  char* ptr = EncodeVarint32(buf, v);  dst->append(buf, ptr - buf);}//对于64位，直接循环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;     //每次提取低7位的数据    v >>= 7;                        //然后右移7位  }  *(ptr++) = static_cast<unsigned char>(v);  return reinterpret_cast<char*>(ptr);}void PutVarint64(std::string* dst, uint64_t v) {  char buf[10];  char* ptr = EncodeVarint64(buf, v);  dst->append(buf, ptr - buf);}

以下是解码

// Lower-level versions of Get... that read directly from a character buffer// without any bounds checking.//32/64位整数解码//这里的char*就是按位存放uint32_t类型的数字的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;  }}

从指针获取int,调用一个回调函数。

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);}}//解析变长编码字符串，返回字符串地址//这里的p才是leveldb定义的字符编码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) {//对于每一个byte,第一位表示还有没有数，为1(byte & 128 = 1),说明还有数据      // More bytes are present      result |= ((byte & 127) << shift);    //获取7bit数据，然后左移shift， 127 = (0111 1111)2    } else {      result |= (byte << shift);        //现在没有后续的数字了，计算好就返回      *value = result;      return reinterpret_cast<const char*>(p);    }  }  return NULL;}