From: alexhz Date: Wed, 15 Jan 2014 11:42:48 +0000 (+0000) Subject: Compact serialization for variable-length integers X-Git-Tag: v0.4.4.7-nvc-next-testing~33 X-Git-Url: https://git.novaco.in/?p=novacoin.git;a=commitdiff_plain;h=b8b636c64f4b611daf4dd9b6cfaf6d6102ac7121 Compact serialization for variable-length integers Variable-length integers: bytes are a MSB base-128 encoding of the number. The high bit in each byte signifies whether another digit follows. To make the encoding is one-to-one, one is subtracted from all but the last digit. Thus, the byte sequence a[] with length len, where all but the last byte has bit 128 set, encodes the number: (a[len-1] & 0x7F) + sum(i=1..len-1, 128^i*((a[len-i-1] & 0x7F)+1)) Properties: * Very small (0-127: 1 byte, 128-16511: 2 bytes, 16512-2113663: 3 bytes) * Every integer has exactly one encoding * Encoding does not depend on size of original integer type --- diff --git a/src/checkpoints.h b/src/checkpoints.h index fedcf36..d5028b3 100644 --- a/src/checkpoints.h +++ b/src/checkpoints.h @@ -8,7 +8,7 @@ #include "net.h" #include "util.h" -#define CHECKPOINT_MAX_SPAN (60 * 60) // max 1 hour before latest block +#define CHECKPOINT_MAX_SPAN (60 * 60) // max 60 minutes before latest block #ifdef WIN32 #undef STRICT diff --git a/src/serialize.h b/src/serialize.h index 3b3dcd4..2ed38ff 100644 --- a/src/serialize.h +++ b/src/serialize.h @@ -244,8 +244,76 @@ uint64 ReadCompactSize(Stream& is) } +// Variable-length integers: bytes are a MSB base-128 encoding of the number. +// The high bit in each byte signifies whether another digit follows. To make +// the encoding is one-to-one, one is subtracted from all but the last digit. +// Thus, the byte sequence a[] with length len, where all but the last byte +// has bit 128 set, encodes the number: +// +// (a[len-1] & 0x7F) + sum(i=1..len-1, 128^i*((a[len-i-1] & 0x7F)+1)) +// +// Properties: +// * Very small (0-127: 1 byte, 128-16511: 2 bytes, 16512-2113663: 3 bytes) +// * Every integer has exactly one encoding +// * Encoding does not depend on size of original integer type +// * No redundancy: every (infinite) byte sequence corresponds to a list +// of encoded integers. +// +// 0: [0x00] 256: [0x81 0x00] +// 1: [0x01] 16383: [0xFE 0x7F] +// 127: [0x7F] 16384: [0xFF 0x00] +// 128: [0x80 0x00] 16511: [0x80 0xFF 0x7F] +// 255: [0x80 0x7F] 65535: [0x82 0xFD 0x7F] +// 2^32: [0x8E 0xFE 0xFE 0xFF 0x00] + +template +inline unsigned int GetSizeOfVarInt(I n) +{ + int nRet = 0; + while(true) { + nRet++; + if (n <= 0x7F) + break; + n = (n >> 7) - 1; + } + return nRet; +} + +template +void WriteVarInt(Stream& os, I n) +{ + unsigned char tmp[(sizeof(n)*8+6)/7]; + int len=0; + while(true) { + tmp[len] = (n & 0x7F) | (len ? 0x80 : 0x00); + if (n <= 0x7F) + break; + n = (n >> 7) - 1; + len++; + } + do { + WRITEDATA(os, tmp[len]); + } while(len--); +} + +template +I ReadVarInt(Stream& is) +{ + I n = 0; + while(true) { + unsigned char chData; + READDATA(is, chData); + n = (n << 7) | (chData & 0x7F); + if (chData & 0x80) + n++; + else + return n; + } +} + #define FLATDATA(obj) REF(CFlatData((char*)&(obj), (char*)&(obj) + sizeof(obj))) +#define VARINT(obj) REF(WrapVarInt(REF(obj))) /** Wrapper for serializing arrays and POD. */ @@ -279,6 +347,32 @@ public: } }; +template +class CVarInt +{ +protected: + I &n; +public: + CVarInt(I& nIn) : n(nIn) { } + + unsigned int GetSerializeSize(int, int) const { + return GetSizeOfVarInt(n); + } + + template + void Serialize(Stream &s, int, int) const { + WriteVarInt(s, n); + } + + template + void Unserialize(Stream& s, int, int) { + n = ReadVarInt(s); + } +}; + +template +CVarInt WrapVarInt(I& n) { return CVarInt(n); } + // // Forward declarations //