// Copyright (c) 2009-2010 Satoshi Nakamoto // Copyright (c) 2009-2015 The Bitcoin Core developers // Distributed under the MIT software license, see the accompanying // file COPYING or http://www.opensource.org/licenses/mit-license.php. #ifndef BITCOIN_SERIALIZE_H #define BITCOIN_SERIALIZE_H #include "compat/endian.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include "prevector.h" static const unsigned int MAX_SIZE = 0x02000000; /** * Dummy data type to identify deserializing constructors. * * By convention, a constructor of a type T with signature * * template T::T(deserialize_type, Stream& s) * * is a deserializing constructor, which builds the type by * deserializing it from s. If T contains const fields, this * is likely the only way to do so. */ struct deserialize_type {}; constexpr deserialize_type deserialize {}; /** * Used to bypass the rule against non-const reference to temporary * where it makes sense with wrappers such as CFlatData or CTxDB */ template inline T& REF(const T& val) { return const_cast(val); } /** * Used to acquire a non-const pointer "this" to generate bodies * of const serialization operations from a template */ template inline T* NCONST_PTR(const T* val) { return const_cast(val); } /** * Important: Do not use the following functions in new code, but use v.data() * and v.data() + v.size() respectively directly. They were once introduced to * have a compatible, safe way to get the begin and end pointer of a vector. * However with C++11 the language has built-in functionality for this and it's * more readable to just use that. */ template inline typename V::value_type* begin_ptr(V& v) { return v.data(); } template inline const typename V::value_type* begin_ptr(const V& v) { return v.data(); } template inline typename V::value_type* end_ptr(V& v) { return v.data() + v.size(); } template inline const typename V::value_type* end_ptr(const V& v) { return v.data() + v.size(); } /* * Lowest-level serialization and conversion. * @note Sizes of these types are verified in the tests */ template inline void ser_writedata8(Stream &s, uint8_t obj) { s.write((char*)&obj, 1); } template inline void ser_writedata16(Stream &s, uint16_t obj) { obj = htole16(obj); s.write((char*)&obj, 2); } template inline void ser_writedata32(Stream &s, uint32_t obj) { obj = htole32(obj); s.write((char*)&obj, 4); } template inline void ser_writedata32be(Stream &s, uint32_t obj) { obj = htobe32(obj); s.write((char*)&obj, 4); } template inline void ser_writedata64(Stream &s, uint64_t obj) { obj = htole64(obj); s.write((char*)&obj, 8); } template inline uint8_t ser_readdata8(Stream &s) { uint8_t obj; s.read((char*)&obj, 1); return obj; } template inline uint16_t ser_readdata16(Stream &s) { uint16_t obj; s.read((char*)&obj, 2); return le16toh(obj); } template inline uint32_t ser_readdata32(Stream &s) { uint32_t obj; s.read((char*)&obj, 4); return le32toh(obj); } template inline uint32_t ser_readdata32be(Stream &s) { uint32_t obj; s.read((char*)&obj, 4); return be32toh(obj); } template inline uint64_t ser_readdata64(Stream &s) { uint64_t obj; s.read((char*)&obj, 8); return le64toh(obj); } inline uint64_t ser_double_to_uint64(double x) { union { double x; uint64_t y; } tmp; tmp.x = x; return tmp.y; } inline uint32_t ser_float_to_uint32(float x) { union { float x; uint32_t y; } tmp; tmp.x = x; return tmp.y; } inline double ser_uint64_to_double(uint64_t y) { union { double x; uint64_t y; } tmp; tmp.y = y; return tmp.x; } inline float ser_uint32_to_float(uint32_t y) { union { float x; uint32_t y; } tmp; tmp.y = y; return tmp.x; } ///////////////////////////////////////////////////////////////// // // Templates for serializing to anything that looks like a stream, // i.e. anything that supports .read(char*, size_t) and .write(char*, size_t) // class CSizeComputer; enum { // primary actions SER_NETWORK = (1 << 0), SER_DISK = (1 << 1), SER_GETHASH = (1 << 2), }; #define READWRITE(obj) (::SerReadWrite(s, (obj), ser_action)) #define READWRITEMANY(...) (::SerReadWriteMany(s, ser_action, __VA_ARGS__)) /** * Implement three methods for serializable objects. These are actually wrappers over * "SerializationOp" template, which implements the body of each class' serialization * code. Adding "ADD_SERIALIZE_METHODS" in the body of the class causes these wrappers to be * added as members. */ #define ADD_SERIALIZE_METHODS \ template \ void Serialize(Stream& s) const { \ NCONST_PTR(this)->SerializationOp(s, CSerActionSerialize()); \ } \ template \ void Unserialize(Stream& s) { \ SerializationOp(s, CSerActionUnserialize()); \ } template inline void Serialize(Stream& s, char a ) { ser_writedata8(s, a); } // TODO Get rid of bare char template inline void Serialize(Stream& s, int8_t a ) { ser_writedata8(s, a); } template inline void Serialize(Stream& s, uint8_t a ) { ser_writedata8(s, a); } template inline void Serialize(Stream& s, int16_t a ) { ser_writedata16(s, a); } template inline void Serialize(Stream& s, uint16_t a) { ser_writedata16(s, a); } template inline void Serialize(Stream& s, int32_t a ) { ser_writedata32(s, a); } template inline void Serialize(Stream& s, uint32_t a) { ser_writedata32(s, a); } template inline void Serialize(Stream& s, int64_t a ) { ser_writedata64(s, a); } template inline void Serialize(Stream& s, uint64_t a) { ser_writedata64(s, a); } template inline void Serialize(Stream& s, float a ) { ser_writedata32(s, ser_float_to_uint32(a)); } template inline void Serialize(Stream& s, double a ) { ser_writedata64(s, ser_double_to_uint64(a)); } template inline void Unserialize(Stream& s, char& a ) { a = ser_readdata8(s); } // TODO Get rid of bare char template inline void Unserialize(Stream& s, int8_t& a ) { a = ser_readdata8(s); } template inline void Unserialize(Stream& s, uint8_t& a ) { a = ser_readdata8(s); } template inline void Unserialize(Stream& s, int16_t& a ) { a = ser_readdata16(s); } template inline void Unserialize(Stream& s, uint16_t& a) { a = ser_readdata16(s); } template inline void Unserialize(Stream& s, int32_t& a ) { a = ser_readdata32(s); } template inline void Unserialize(Stream& s, uint32_t& a) { a = ser_readdata32(s); } template inline void Unserialize(Stream& s, int64_t& a ) { a = ser_readdata64(s); } template inline void Unserialize(Stream& s, uint64_t& a) { a = ser_readdata64(s); } template inline void Unserialize(Stream& s, float& a ) { a = ser_uint32_to_float(ser_readdata32(s)); } template inline void Unserialize(Stream& s, double& a ) { a = ser_uint64_to_double(ser_readdata64(s)); } template inline void Serialize(Stream& s, bool a) { char f=a; ser_writedata8(s, f); } template inline void Unserialize(Stream& s, bool& a) { char f=ser_readdata8(s); a=f; } /** * Compact Size * size < 253 -- 1 byte * size <= USHRT_MAX -- 3 bytes (253 + 2 bytes) * size <= UINT_MAX -- 5 bytes (254 + 4 bytes) * size > UINT_MAX -- 9 bytes (255 + 8 bytes) */ inline unsigned int GetSizeOfCompactSize(uint64_t nSize) { if (nSize < 253) return sizeof(unsigned char); else if (nSize <= std::numeric_limits::max()) return sizeof(unsigned char) + sizeof(unsigned short); else if (nSize <= std::numeric_limits::max()) return sizeof(unsigned char) + sizeof(unsigned int); else return sizeof(unsigned char) + sizeof(uint64_t); } inline void WriteCompactSize(CSizeComputer& os, uint64_t nSize); template void WriteCompactSize(Stream& os, uint64_t nSize) { if (nSize < 253) { ser_writedata8(os, nSize); } else if (nSize <= std::numeric_limits::max()) { ser_writedata8(os, 253); ser_writedata16(os, nSize); } else if (nSize <= std::numeric_limits::max()) { ser_writedata8(os, 254); ser_writedata32(os, nSize); } else { ser_writedata8(os, 255); ser_writedata64(os, nSize); } return; } template uint64_t ReadCompactSize(Stream& is) { uint8_t chSize = ser_readdata8(is); uint64_t nSizeRet = 0; if (chSize < 253) { nSizeRet = chSize; } else if (chSize == 253) { nSizeRet = ser_readdata16(is); if (nSizeRet < 253) throw std::ios_base::failure("non-canonical ReadCompactSize()"); } else if (chSize == 254) { nSizeRet = ser_readdata32(is); if (nSizeRet < 0x10000u) throw std::ios_base::failure("non-canonical ReadCompactSize()"); } else { nSizeRet = ser_readdata64(is); if (nSizeRet < 0x100000000ULL) throw std::ios_base::failure("non-canonical ReadCompactSize()"); } if (nSizeRet > (uint64_t)MAX_SIZE) throw std::ios_base::failure("ReadCompactSize(): size too large"); return nSizeRet; } /** * 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 * sure 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: [0xFF 0x7F] * 255: [0x80 0x7F] 65535: [0x82 0xFE 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 inline void WriteVarInt(CSizeComputer& os, I n); 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 { ser_writedata8(os, tmp[len]); } while(len--); } template I ReadVarInt(Stream& is) { I n = 0; while(true) { unsigned char chData = ser_readdata8(is); 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))) #define COMPACTSIZE(obj) REF(CCompactSize(REF(obj))) #define LIMITED_STRING(obj,n) REF(LimitedString< n >(REF(obj))) /** * Wrapper for serializing arrays and POD. */ class CFlatData { protected: char* pbegin; char* pend; public: CFlatData(void* pbeginIn, void* pendIn) : pbegin((char*)pbeginIn), pend((char*)pendIn) { } template explicit CFlatData(std::vector &v) { pbegin = (char*)begin_ptr(v); pend = (char*)end_ptr(v); } template explicit CFlatData(prevector &v) { pbegin = (char*)begin_ptr(v); pend = (char*)end_ptr(v); } char* begin() { return pbegin; } const char* begin() const { return pbegin; } char* end() { return pend; } const char* end() const { return pend; } template void Serialize(Stream& s) const { s.write(pbegin, pend - pbegin); } template void Unserialize(Stream& s) { s.read(pbegin, pend - pbegin); } }; template class CVarInt { protected: I &n; public: CVarInt(I& nIn) : n(nIn) { } template void Serialize(Stream &s) const { WriteVarInt(s, n); } template void Unserialize(Stream& s) { n = ReadVarInt(s); } }; class CCompactSize { protected: uint64_t &n; public: CCompactSize(uint64_t& nIn) : n(nIn) { } unsigned int GetSerializeSize() const { return GetSizeOfCompactSize(n); } template void Serialize(Stream &s) const { WriteCompactSize(s, n); } template void Unserialize(Stream& s) { n = ReadCompactSize(s); } }; template class LimitedString { protected: std::string& string; public: LimitedString(std::string& _string) : string(_string) {} template void Unserialize(Stream& s) { size_t size = ReadCompactSize(s); if (size > Limit) { throw std::ios_base::failure("String length limit exceeded"); } string.resize(size); if (size != 0) s.read((char*)&string[0], size); } template void Serialize(Stream& s) const { WriteCompactSize(s, string.size()); if (!string.empty()) s.write((char*)&string[0], string.size()); } }; template CVarInt WrapVarInt(I& n) { return CVarInt(n); } /** * Forward declarations */ /** * string */ template void Serialize(Stream& os, const std::basic_string& str); template void Unserialize(Stream& is, std::basic_string& str); /** * prevector * prevectors of unsigned char are a special case and are intended to be serialized as a single opaque blob. */ template void Serialize_impl(Stream& os, const prevector& v, const unsigned char&); template void Serialize_impl(Stream& os, const prevector& v, const V&); template inline void Serialize(Stream& os, const prevector& v); template void Unserialize_impl(Stream& is, prevector& v, const unsigned char&); template void Unserialize_impl(Stream& is, prevector& v, const V&); template inline void Unserialize(Stream& is, prevector& v); /** * vector * vectors of unsigned char are a special case and are intended to be serialized as a single opaque blob. */ template void Serialize_impl(Stream& os, const std::vector& v, const unsigned char&); template void Serialize_impl(Stream& os, const std::vector& v, const V&); template inline void Serialize(Stream& os, const std::vector& v); template void Unserialize_impl(Stream& is, std::vector& v, const unsigned char&); template void Unserialize_impl(Stream& is, std::vector& v, const V&); template inline void Unserialize(Stream& is, std::vector& v); /** * pair */ template void Serialize(Stream& os, const std::pair& item); template void Unserialize(Stream& is, std::pair& item); /** * map */ template void Serialize(Stream& os, const std::map& m); template void Unserialize(Stream& is, std::map& m); /** * set */ template void Serialize(Stream& os, const std::set& m); template void Unserialize(Stream& is, std::set& m); /** * shared_ptr */ template void Serialize(Stream& os, const std::shared_ptr& p); template void Unserialize(Stream& os, std::shared_ptr& p); /** * unique_ptr */ template void Serialize(Stream& os, const std::unique_ptr& p); template void Unserialize(Stream& os, std::unique_ptr& p); /** * If none of the specialized versions above matched, default to calling member function. */ template inline void Serialize(Stream& os, const T& a) { a.Serialize(os); } template inline void Unserialize(Stream& is, T& a) { a.Unserialize(is); } /** * string */ template void Serialize(Stream& os, const std::basic_string& str) { WriteCompactSize(os, str.size()); if (!str.empty()) os.write((char*)&str[0], str.size() * sizeof(str[0])); } template void Unserialize(Stream& is, std::basic_string& str) { unsigned int nSize = ReadCompactSize(is); str.resize(nSize); if (nSize != 0) is.read((char*)&str[0], nSize * sizeof(str[0])); } /** * prevector */ template void Serialize_impl(Stream& os, const prevector& v, const unsigned char&) { WriteCompactSize(os, v.size()); if (!v.empty()) os.write((char*)&v[0], v.size() * sizeof(T)); } template void Serialize_impl(Stream& os, const prevector& v, const V&) { WriteCompactSize(os, v.size()); for (typename prevector::const_iterator vi = v.begin(); vi != v.end(); ++vi) ::Serialize(os, (*vi)); } template inline void Serialize(Stream& os, const prevector& v) { Serialize_impl(os, v, T()); } template void Unserialize_impl(Stream& is, prevector& v, const unsigned char&) { // Limit size per read so bogus size value won't cause out of memory v.clear(); unsigned int nSize = ReadCompactSize(is); unsigned int i = 0; while (i < nSize) { unsigned int blk = std::min(nSize - i, (unsigned int)(1 + 4999999 / sizeof(T))); v.resize(i + blk); is.read((char*)&v[i], blk * sizeof(T)); i += blk; } } template void Unserialize_impl(Stream& is, prevector& v, const V&) { v.clear(); unsigned int nSize = ReadCompactSize(is); unsigned int i = 0; unsigned int nMid = 0; while (nMid < nSize) { nMid += 5000000 / sizeof(T); if (nMid > nSize) nMid = nSize; v.resize(nMid); for (; i < nMid; i++) Unserialize(is, v[i]); } } template inline void Unserialize(Stream& is, prevector& v) { Unserialize_impl(is, v, T()); } /** * vector */ template void Serialize_impl(Stream& os, const std::vector& v, const unsigned char&) { WriteCompactSize(os, v.size()); if (!v.empty()) os.write((char*)&v[0], v.size() * sizeof(T)); } template void Serialize_impl(Stream& os, const std::vector& v, const V&) { WriteCompactSize(os, v.size()); for (typename std::vector::const_iterator vi = v.begin(); vi != v.end(); ++vi) ::Serialize(os, (*vi)); } template inline void Serialize(Stream& os, const std::vector& v) { Serialize_impl(os, v, T()); } template void Unserialize_impl(Stream& is, std::vector& v, const unsigned char&) { // Limit size per read so bogus size value won't cause out of memory v.clear(); unsigned int nSize = ReadCompactSize(is); unsigned int i = 0; while (i < nSize) { unsigned int blk = std::min(nSize - i, (unsigned int)(1 + 4999999 / sizeof(T))); v.resize(i + blk); is.read((char*)&v[i], blk * sizeof(T)); i += blk; } } template void Unserialize_impl(Stream& is, std::vector& v, const V&) { v.clear(); unsigned int nSize = ReadCompactSize(is); unsigned int i = 0; unsigned int nMid = 0; while (nMid < nSize) { nMid += 5000000 / sizeof(T); if (nMid > nSize) nMid = nSize; v.resize(nMid); for (; i < nMid; i++) Unserialize(is, v[i]); } } template inline void Unserialize(Stream& is, std::vector& v) { Unserialize_impl(is, v, T()); } /** * pair */ template void Serialize(Stream& os, const std::pair& item) { Serialize(os, item.first); Serialize(os, item.second); } template void Unserialize(Stream& is, std::pair& item) { Unserialize(is, item.first); Unserialize(is, item.second); } /** * map */ template void Serialize(Stream& os, const std::map& m) { WriteCompactSize(os, m.size()); for (typename std::map::const_iterator mi = m.begin(); mi != m.end(); ++mi) Serialize(os, (*mi)); } template void Unserialize(Stream& is, std::map& m) { m.clear(); unsigned int nSize = ReadCompactSize(is); typename std::map::iterator mi = m.begin(); for (unsigned int i = 0; i < nSize; i++) { std::pair item; Unserialize(is, item); mi = m.insert(mi, item); } } /** * set */ template void Serialize(Stream& os, const std::set& m) { WriteCompactSize(os, m.size()); for (typename std::set::const_iterator it = m.begin(); it != m.end(); ++it) Serialize(os, (*it)); } template void Unserialize(Stream& is, std::set& m) { m.clear(); unsigned int nSize = ReadCompactSize(is); typename std::set::iterator it = m.begin(); for (unsigned int i = 0; i < nSize; i++) { K key; Unserialize(is, key); it = m.insert(it, key); } } /** * list */ template void Serialize(Stream& os, const std::list& l) { WriteCompactSize(os, l.size()); for (typename std::list::const_iterator it = l.begin(); it != l.end(); ++it) Serialize(os, (*it)); } template void Unserialize(Stream& is, std::list& l) { l.clear(); unsigned int nSize = ReadCompactSize(is); for (unsigned int i = 0; i < nSize; i++) { T val; Unserialize(is, val); l.push_back(val); } } /** * unique_ptr */ template void Serialize(Stream& os, const std::unique_ptr& p) { Serialize(os, *p); } template void Unserialize(Stream& is, std::unique_ptr& p) { p.reset(new T(deserialize, is)); } /** * shared_ptr */ template void Serialize(Stream& os, const std::shared_ptr& p) { Serialize(os, *p); } template void Unserialize(Stream& is, std::shared_ptr& p) { p = std::make_shared(deserialize, is); } /** * Support for ADD_SERIALIZE_METHODS and READWRITE macro */ struct CSerActionSerialize { constexpr bool ForRead() const { return false; } }; struct CSerActionUnserialize { constexpr bool ForRead() const { return true; } }; template inline void SerReadWrite(Stream& s, const T& obj, CSerActionSerialize ser_action) { ::Serialize(s, obj); } template inline void SerReadWrite(Stream& s, T& obj, CSerActionUnserialize ser_action) { ::Unserialize(s, obj); } /* ::GetSerializeSize implementations * * Computing the serialized size of objects is done through a special stream * object of type CSizeComputer, which only records the number of bytes written * to it. * * If your Serialize or SerializationOp method has non-trivial overhead for * serialization, it may be worthwhile to implement a specialized version for * CSizeComputer, which uses the s.seek() method to record bytes that would * be written instead. */ class CSizeComputer { protected: size_t nSize; const int nType; const int nVersion; public: CSizeComputer(int nTypeIn, int nVersionIn) : nSize(0), nType(nTypeIn), nVersion(nVersionIn) {} void write(const char *psz, size_t _nSize) { this->nSize += _nSize; } /** Pretend _nSize bytes are written, without specifying them. */ void seek(size_t _nSize) { this->nSize += _nSize; } template CSizeComputer& operator<<(const T& obj) { ::Serialize(*this, obj); return (*this); } size_t size() const { return nSize; } int GetVersion() const { return nVersion; } int GetType() const { return nType; } }; template void SerializeMany(Stream& s) { } template void SerializeMany(Stream& s, Arg&& arg) { ::Serialize(s, std::forward(arg)); } template void SerializeMany(Stream& s, Arg&& arg, Args&&... args) { ::Serialize(s, std::forward(arg)); ::SerializeMany(s, std::forward(args)...); } template inline void UnserializeMany(Stream& s) { } template inline void UnserializeMany(Stream& s, Arg& arg) { ::Unserialize(s, arg); } template inline void UnserializeMany(Stream& s, Arg& arg, Args&... args) { ::Unserialize(s, arg); ::UnserializeMany(s, args...); } template inline void SerReadWriteMany(Stream& s, CSerActionSerialize ser_action, Args&&... args) { ::SerializeMany(s, std::forward(args)...); } template inline void SerReadWriteMany(Stream& s, CSerActionUnserialize ser_action, Args&... args) { ::UnserializeMany(s, args...); } template inline void WriteVarInt(CSizeComputer &s, I n) { s.seek(GetSizeOfVarInt(n)); } inline void WriteCompactSize(CSizeComputer &s, uint64_t nSize) { s.seek(GetSizeOfCompactSize(nSize)); } template size_t GetSerializeSize(const T& t, int nType, int nVersion = 0) { return (CSizeComputer(nType, nVersion) << t).size(); } template size_t GetSerializeSize(const S& s, const T& t) { return (CSizeComputer(s.GetType(), s.GetVersion()) << t).size(); } #endif // BITCOIN_SERIALIZE_H