leveldb中,数字的存储统一采用小端序,通过对数字编码和压缩,节省了存储空间。
变长编码
小端序中,每个字节的最低位存储状态,其余7位存储数据。
status状态值说明:
- 1:该字节不是当前数字最后一个字节;
- 0:该字节是当前数字最后一个字节;
编码
以数字1562357为为例:
uint32_t变长编码
char* EncodeVarint32(char* dst, uint32_t v) {
uint8_t* ptr = reinterpret_cast<uint8_t*>(dst);
static const int B = 128; // 0x10000000
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);
}
uint64_t编码
char* EncodeVarint64(char* dst, uint64_t v) {
static const int B = 128; // 0x10000000
uint8_t* ptr = reinterpret_cast<uint8_t*>(dst);
while (v >= B) {
*(ptr++) = v | B;
v >>= 7;
}
*(ptr++) = static_cast<uint8_t>(v);
return reinterpret_cast<char*>(ptr);
}
解码
uint32_t解码
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 uint8_t*>(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;
}
uint64_t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 uint8_t*>(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;
}