go-ethereum/rlp/encode.go
Felix Lange 9b93564e21
rlp/rlpgen: RLP encoder code generator (#24251)
This change adds a code generator tool for creating EncodeRLP method
implementations. The generated methods will behave identically to the
reflect-based encoder, but run faster because there is no reflection overhead.

Package rlp now provides the EncoderBuffer type for incremental encoding. This
is used by generated code, but the new methods can also be useful for
hand-written encoders.

There is also experimental support for generating DecodeRLP, and some new
methods have been added to the existing Stream type to support this. Creating
decoders with rlpgen is not recommended at this time because the generated
methods create very poor error reporting.

More detail about package rlp changes:

* rlp: externalize struct field processing / validation

This adds a new package, rlp/internal/rlpstruct, in preparation for the
RLP encoder generator.

I think the struct field rules are subtle enough to warrant extracting
this into their own package, even though it means that a bunch of
adapter code is needed for converting to/from rlpstruct.Type.

* rlp: add more decoder methods (for rlpgen)

This adds new methods on rlp.Stream:

- Uint64, Uint32, Uint16, Uint8, BigInt
- ReadBytes for decoding into []byte
- MoreDataInList - useful for optional list elements

* rlp: expose encoder buffer (for rlpgen)

This exposes the internal encoder buffer type for use in EncodeRLP
implementations.

The new EncoderBuffer type is a sort-of 'opaque handle' for a pointer to
encBuffer. It is implemented this way to ensure the global encBuffer pool
is handled correctly.
2022-02-16 18:14:12 +01:00

476 lines
12 KiB
Go

// Copyright 2014 The go-ethereum Authors
// This file is part of the go-ethereum library.
//
// The go-ethereum library is free software: you can redistribute it and/or modify
// it under the terms of the GNU Lesser General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// The go-ethereum library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public License
// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.
package rlp
import (
"errors"
"fmt"
"io"
"math/big"
"reflect"
"github.com/ethereum/go-ethereum/rlp/internal/rlpstruct"
)
var (
// Common encoded values.
// These are useful when implementing EncodeRLP.
EmptyString = []byte{0x80}
EmptyList = []byte{0xC0}
)
var ErrNegativeBigInt = errors.New("rlp: cannot encode negative big.Int")
// Encoder is implemented by types that require custom
// encoding rules or want to encode private fields.
type Encoder interface {
// EncodeRLP should write the RLP encoding of its receiver to w.
// If the implementation is a pointer method, it may also be
// called for nil pointers.
//
// Implementations should generate valid RLP. The data written is
// not verified at the moment, but a future version might. It is
// recommended to write only a single value but writing multiple
// values or no value at all is also permitted.
EncodeRLP(io.Writer) error
}
// Encode writes the RLP encoding of val to w. Note that Encode may
// perform many small writes in some cases. Consider making w
// buffered.
//
// Please see package-level documentation of encoding rules.
func Encode(w io.Writer, val interface{}) error {
// Optimization: reuse *encBuffer when called by EncodeRLP.
if buf, ok := w.(*encBuffer); ok {
return buf.encode(val)
}
if ebuf, ok := w.(EncoderBuffer); ok {
return ebuf.buf.encode(val)
}
buf := getEncBuffer()
defer encBufferPool.Put(buf)
if err := buf.encode(val); err != nil {
return err
}
return buf.toWriter(w)
}
// EncodeToBytes returns the RLP encoding of val.
// Please see package-level documentation for the encoding rules.
func EncodeToBytes(val interface{}) ([]byte, error) {
buf := getEncBuffer()
defer encBufferPool.Put(buf)
if err := buf.encode(val); err != nil {
return nil, err
}
return buf.toBytes(), nil
}
// EncodeToReader returns a reader from which the RLP encoding of val
// can be read. The returned size is the total size of the encoded
// data.
//
// Please see the documentation of Encode for the encoding rules.
func EncodeToReader(val interface{}) (size int, r io.Reader, err error) {
buf := getEncBuffer()
if err := buf.encode(val); err != nil {
encBufferPool.Put(buf)
return 0, nil, err
}
// Note: can't put the reader back into the pool here
// because it is held by encReader. The reader puts it
// back when it has been fully consumed.
return buf.size(), &encReader{buf: buf}, nil
}
type listhead struct {
offset int // index of this header in string data
size int // total size of encoded data (including list headers)
}
// encode writes head to the given buffer, which must be at least
// 9 bytes long. It returns the encoded bytes.
func (head *listhead) encode(buf []byte) []byte {
return buf[:puthead(buf, 0xC0, 0xF7, uint64(head.size))]
}
// headsize returns the size of a list or string header
// for a value of the given size.
func headsize(size uint64) int {
if size < 56 {
return 1
}
return 1 + intsize(size)
}
// puthead writes a list or string header to buf.
// buf must be at least 9 bytes long.
func puthead(buf []byte, smalltag, largetag byte, size uint64) int {
if size < 56 {
buf[0] = smalltag + byte(size)
return 1
}
sizesize := putint(buf[1:], size)
buf[0] = largetag + byte(sizesize)
return sizesize + 1
}
var encoderInterface = reflect.TypeOf(new(Encoder)).Elem()
// makeWriter creates a writer function for the given type.
func makeWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
kind := typ.Kind()
switch {
case typ == rawValueType:
return writeRawValue, nil
case typ.AssignableTo(reflect.PtrTo(bigInt)):
return writeBigIntPtr, nil
case typ.AssignableTo(bigInt):
return writeBigIntNoPtr, nil
case kind == reflect.Ptr:
return makePtrWriter(typ, ts)
case reflect.PtrTo(typ).Implements(encoderInterface):
return makeEncoderWriter(typ), nil
case isUint(kind):
return writeUint, nil
case kind == reflect.Bool:
return writeBool, nil
case kind == reflect.String:
return writeString, nil
case kind == reflect.Slice && isByte(typ.Elem()):
return writeBytes, nil
case kind == reflect.Array && isByte(typ.Elem()):
return makeByteArrayWriter(typ), nil
case kind == reflect.Slice || kind == reflect.Array:
return makeSliceWriter(typ, ts)
case kind == reflect.Struct:
return makeStructWriter(typ)
case kind == reflect.Interface:
return writeInterface, nil
default:
return nil, fmt.Errorf("rlp: type %v is not RLP-serializable", typ)
}
}
func writeRawValue(val reflect.Value, w *encBuffer) error {
w.str = append(w.str, val.Bytes()...)
return nil
}
func writeUint(val reflect.Value, w *encBuffer) error {
w.writeUint64(val.Uint())
return nil
}
func writeBool(val reflect.Value, w *encBuffer) error {
w.writeBool(val.Bool())
return nil
}
func writeBigIntPtr(val reflect.Value, w *encBuffer) error {
ptr := val.Interface().(*big.Int)
if ptr == nil {
w.str = append(w.str, 0x80)
return nil
}
if ptr.Sign() == -1 {
return ErrNegativeBigInt
}
w.writeBigInt(ptr)
return nil
}
func writeBigIntNoPtr(val reflect.Value, w *encBuffer) error {
i := val.Interface().(big.Int)
if i.Sign() == -1 {
return ErrNegativeBigInt
}
w.writeBigInt(&i)
return nil
}
func writeBytes(val reflect.Value, w *encBuffer) error {
w.writeBytes(val.Bytes())
return nil
}
func makeByteArrayWriter(typ reflect.Type) writer {
switch typ.Len() {
case 0:
return writeLengthZeroByteArray
case 1:
return writeLengthOneByteArray
default:
length := typ.Len()
return func(val reflect.Value, w *encBuffer) error {
if !val.CanAddr() {
// Getting the byte slice of val requires it to be addressable. Make it
// addressable by copying.
copy := reflect.New(val.Type()).Elem()
copy.Set(val)
val = copy
}
slice := byteArrayBytes(val, length)
w.encodeStringHeader(len(slice))
w.str = append(w.str, slice...)
return nil
}
}
}
func writeLengthZeroByteArray(val reflect.Value, w *encBuffer) error {
w.str = append(w.str, 0x80)
return nil
}
func writeLengthOneByteArray(val reflect.Value, w *encBuffer) error {
b := byte(val.Index(0).Uint())
if b <= 0x7f {
w.str = append(w.str, b)
} else {
w.str = append(w.str, 0x81, b)
}
return nil
}
func writeString(val reflect.Value, w *encBuffer) error {
s := val.String()
if len(s) == 1 && s[0] <= 0x7f {
// fits single byte, no string header
w.str = append(w.str, s[0])
} else {
w.encodeStringHeader(len(s))
w.str = append(w.str, s...)
}
return nil
}
func writeInterface(val reflect.Value, w *encBuffer) error {
if val.IsNil() {
// Write empty list. This is consistent with the previous RLP
// encoder that we had and should therefore avoid any
// problems.
w.str = append(w.str, 0xC0)
return nil
}
eval := val.Elem()
writer, err := cachedWriter(eval.Type())
if err != nil {
return err
}
return writer(eval, w)
}
func makeSliceWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
etypeinfo := theTC.infoWhileGenerating(typ.Elem(), rlpstruct.Tags{})
if etypeinfo.writerErr != nil {
return nil, etypeinfo.writerErr
}
var wfn writer
if ts.Tail {
// This is for struct tail slices.
// w.list is not called for them.
wfn = func(val reflect.Value, w *encBuffer) error {
vlen := val.Len()
for i := 0; i < vlen; i++ {
if err := etypeinfo.writer(val.Index(i), w); err != nil {
return err
}
}
return nil
}
} else {
// This is for regular slices and arrays.
wfn = func(val reflect.Value, w *encBuffer) error {
vlen := val.Len()
if vlen == 0 {
w.str = append(w.str, 0xC0)
return nil
}
listOffset := w.list()
for i := 0; i < vlen; i++ {
if err := etypeinfo.writer(val.Index(i), w); err != nil {
return err
}
}
w.listEnd(listOffset)
return nil
}
}
return wfn, nil
}
func makeStructWriter(typ reflect.Type) (writer, error) {
fields, err := structFields(typ)
if err != nil {
return nil, err
}
for _, f := range fields {
if f.info.writerErr != nil {
return nil, structFieldError{typ, f.index, f.info.writerErr}
}
}
var writer writer
firstOptionalField := firstOptionalField(fields)
if firstOptionalField == len(fields) {
// This is the writer function for structs without any optional fields.
writer = func(val reflect.Value, w *encBuffer) error {
lh := w.list()
for _, f := range fields {
if err := f.info.writer(val.Field(f.index), w); err != nil {
return err
}
}
w.listEnd(lh)
return nil
}
} else {
// If there are any "optional" fields, the writer needs to perform additional
// checks to determine the output list length.
writer = func(val reflect.Value, w *encBuffer) error {
lastField := len(fields) - 1
for ; lastField >= firstOptionalField; lastField-- {
if !val.Field(fields[lastField].index).IsZero() {
break
}
}
lh := w.list()
for i := 0; i <= lastField; i++ {
if err := fields[i].info.writer(val.Field(fields[i].index), w); err != nil {
return err
}
}
w.listEnd(lh)
return nil
}
}
return writer, nil
}
func makePtrWriter(typ reflect.Type, ts rlpstruct.Tags) (writer, error) {
nilEncoding := byte(0xC0)
if typeNilKind(typ.Elem(), ts) == String {
nilEncoding = 0x80
}
etypeinfo := theTC.infoWhileGenerating(typ.Elem(), rlpstruct.Tags{})
if etypeinfo.writerErr != nil {
return nil, etypeinfo.writerErr
}
writer := func(val reflect.Value, w *encBuffer) error {
if ev := val.Elem(); ev.IsValid() {
return etypeinfo.writer(ev, w)
}
w.str = append(w.str, nilEncoding)
return nil
}
return writer, nil
}
func makeEncoderWriter(typ reflect.Type) writer {
if typ.Implements(encoderInterface) {
return func(val reflect.Value, w *encBuffer) error {
return val.Interface().(Encoder).EncodeRLP(w)
}
}
w := func(val reflect.Value, w *encBuffer) error {
if !val.CanAddr() {
// package json simply doesn't call MarshalJSON for this case, but encodes the
// value as if it didn't implement the interface. We don't want to handle it that
// way.
return fmt.Errorf("rlp: unadressable value of type %v, EncodeRLP is pointer method", val.Type())
}
return val.Addr().Interface().(Encoder).EncodeRLP(w)
}
return w
}
// putint writes i to the beginning of b in big endian byte
// order, using the least number of bytes needed to represent i.
func putint(b []byte, i uint64) (size int) {
switch {
case i < (1 << 8):
b[0] = byte(i)
return 1
case i < (1 << 16):
b[0] = byte(i >> 8)
b[1] = byte(i)
return 2
case i < (1 << 24):
b[0] = byte(i >> 16)
b[1] = byte(i >> 8)
b[2] = byte(i)
return 3
case i < (1 << 32):
b[0] = byte(i >> 24)
b[1] = byte(i >> 16)
b[2] = byte(i >> 8)
b[3] = byte(i)
return 4
case i < (1 << 40):
b[0] = byte(i >> 32)
b[1] = byte(i >> 24)
b[2] = byte(i >> 16)
b[3] = byte(i >> 8)
b[4] = byte(i)
return 5
case i < (1 << 48):
b[0] = byte(i >> 40)
b[1] = byte(i >> 32)
b[2] = byte(i >> 24)
b[3] = byte(i >> 16)
b[4] = byte(i >> 8)
b[5] = byte(i)
return 6
case i < (1 << 56):
b[0] = byte(i >> 48)
b[1] = byte(i >> 40)
b[2] = byte(i >> 32)
b[3] = byte(i >> 24)
b[4] = byte(i >> 16)
b[5] = byte(i >> 8)
b[6] = byte(i)
return 7
default:
b[0] = byte(i >> 56)
b[1] = byte(i >> 48)
b[2] = byte(i >> 40)
b[3] = byte(i >> 32)
b[4] = byte(i >> 24)
b[5] = byte(i >> 16)
b[6] = byte(i >> 8)
b[7] = byte(i)
return 8
}
}
// intsize computes the minimum number of bytes required to store i.
func intsize(i uint64) (size int) {
for size = 1; ; size++ {
if i >>= 8; i == 0 {
return size
}
}
}