golang__protobuf/proto/decode.go

// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package proto

/*
 * Routines for decoding protocol buffer data to construct in-memory representations.
 */

import (
	"errors"
	"fmt"
	"io"
)

// errOverflow is returned when an integer is too large to be represented.
var errOverflow = errors.New("proto: integer overflow")

// DecodeVarint reads a varint-encoded integer from the slice.
// It returns the integer and the number of bytes consumed, or
// zero if there is not enough.
// This is the format for the
// int32, int64, uint32, uint64, bool, and enum
// protocol buffer types.
func DecodeVarint(buf []byte) (x uint64, n int) {
	for shift := uint(0); shift < 64; shift += 7 {
		if n >= len(buf) {
			return 0, 0
		}
		b := uint64(buf[n])
		n++
		x |= (b & 0x7F) << shift
		if (b & 0x80) == 0 {
			return x, n
		}
	}

	// The number is too large to represent in a 64-bit value.
	return 0, 0
}

func (p *Buffer) decodeVarintSlow() (x uint64, err error) {
	i := p.index
	l := len(p.buf)

	for shift := uint(0); shift < 64; shift += 7 {
		if i >= l {
			err = io.ErrUnexpectedEOF
			return
		}
		b := p.buf[i]
		i++
		x |= (uint64(b) & 0x7F) << shift
		if b < 0x80 {
			p.index = i
			return
		}
	}

	// The number is too large to represent in a 64-bit value.
	err = errOverflow
	return
}

// DecodeVarint reads a varint-encoded integer from the Buffer.
// This is the format for the
// int32, int64, uint32, uint64, bool, and enum
// protocol buffer types.
func (p *Buffer) DecodeVarint() (x uint64, err error) {
	i := p.index
	buf := p.buf

	if i >= len(buf) {
		return 0, io.ErrUnexpectedEOF
	} else if buf[i] < 0x80 {
		p.index++
		return uint64(buf[i]), nil
	} else if len(buf)-i < 10 {
		return p.decodeVarintSlow()
	}

	var b uint64
	// we already checked the first byte
	x = uint64(buf[i]) - 0x80
	i++

	b = uint64(buf[i])
	i++
	x += b << 7
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 7

	b = uint64(buf[i])
	i++
	x += b << 14
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 14

	b = uint64(buf[i])
	i++
	x += b << 21
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 21

	b = uint64(buf[i])
	i++
	x += b << 28
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 28

	b = uint64(buf[i])
	i++
	x += b << 35
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 35

	b = uint64(buf[i])
	i++
	x += b << 42
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 42

	b = uint64(buf[i])
	i++
	x += b << 49
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 49

	b = uint64(buf[i])
	i++
	x += b << 56
	if b&0x80 == 0 {
		goto done
	}
	x -= 0x80 << 56

	b = uint64(buf[i])
	i++
	x += b << 63
	if b&0x80 == 0 {
		goto done
	}

	return 0, errOverflow

done:
	p.index = i
	return x, nil
}

// DecodeFixed64 reads a 64-bit integer from the Buffer.
// This is the format for the
// fixed64, sfixed64, and double protocol buffer types.
func (p *Buffer) DecodeFixed64() (x uint64, err error) {
	// x, err already 0
	i := p.index + 8
	if i < 0 || i > len(p.buf) {
		err = io.ErrUnexpectedEOF
		return
	}
	p.index = i

	x = uint64(p.buf[i-8])
	x |= uint64(p.buf[i-7]) << 8
	x |= uint64(p.buf[i-6]) << 16
	x |= uint64(p.buf[i-5]) << 24
	x |= uint64(p.buf[i-4]) << 32
	x |= uint64(p.buf[i-3]) << 40
	x |= uint64(p.buf[i-2]) << 48
	x |= uint64(p.buf[i-1]) << 56
	return
}

// DecodeFixed32 reads a 32-bit integer from the Buffer.
// This is the format for the
// fixed32, sfixed32, and float protocol buffer types.
func (p *Buffer) DecodeFixed32() (x uint64, err error) {
	// x, err already 0
	i := p.index + 4
	if i < 0 || i > len(p.buf) {
		err = io.ErrUnexpectedEOF
		return
	}
	p.index = i

	x = uint64(p.buf[i-4])
	x |= uint64(p.buf[i-3]) << 8
	x |= uint64(p.buf[i-2]) << 16
	x |= uint64(p.buf[i-1]) << 24
	return
}

// DecodeZigzag64 reads a zigzag-encoded 64-bit integer
// from the Buffer.
// This is the format used for the sint64 protocol buffer type.
func (p *Buffer) DecodeZigzag64() (x uint64, err error) {
	x, err = p.DecodeVarint()
	if err != nil {
		return
	}
	x = (x >> 1) ^ uint64((int64(x&1)<<63)>>63)
	return
}

// DecodeZigzag32 reads a zigzag-encoded 32-bit integer
// from  the Buffer.
// This is the format used for the sint32 protocol buffer type.
func (p *Buffer) DecodeZigzag32() (x uint64, err error) {
	x, err = p.DecodeVarint()
	if err != nil {
		return
	}
	x = uint64((uint32(x) >> 1) ^ uint32((int32(x&1)<<31)>>31))
	return
}

// DecodeRawBytes reads a count-delimited byte buffer from the Buffer.
// This is the format used for the bytes protocol buffer
// type and for embedded messages.
func (p *Buffer) DecodeRawBytes(alloc bool) (buf []byte, err error) {
	n, err := p.DecodeVarint()
	if err != nil {
		return nil, err
	}

	nb := int(n)
	if nb < 0 {
		return nil, fmt.Errorf("proto: bad byte length %d", nb)
	}
	end := p.index + nb
	if end < p.index || end > len(p.buf) {
		return nil, io.ErrUnexpectedEOF
	}

	if !alloc {
		// todo: check if can get more uses of alloc=false
		buf = p.buf[p.index:end]
		p.index += nb
		return
	}

	buf = make([]byte, nb)
	copy(buf, p.buf[p.index:])
	p.index += nb
	return
}

// DecodeStringBytes reads an encoded string from the Buffer.
// This is the format used for the proto2 string type.
func (p *Buffer) DecodeStringBytes() (s string, err error) {
	buf, err := p.DecodeRawBytes(false)
	if err != nil {
		return
	}
	return string(buf), nil
}

// Unmarshaler is the interface representing objects that can
// unmarshal themselves.  The argument points to data that may be
// overwritten, so implementations should not keep references to the
// buffer.
// Unmarshal implementations should not clear the receiver.
// Any unmarshaled data should be merged into the receiver.
// Callers of Unmarshal that do not want to retain existing data
// should Reset the receiver before calling Unmarshal.
type Unmarshaler interface {
	Unmarshal([]byte) error
}

// newUnmarshaler is the interface representing objects that can
// unmarshal themselves. The semantics are identical to Unmarshaler.
//
// This exists to support protoc-gen-go generated messages.
// The proto package will stop type-asserting to this interface in the future.
//
// DO NOT DEPEND ON THIS.
type newUnmarshaler interface {
	XXX_Unmarshal([]byte) error
}

// Unmarshal parses the protocol buffer representation in buf and places the
// decoded result in pb.  If the struct underlying pb does not match
// the data in buf, the results can be unpredictable.
//
// Unmarshal resets pb before starting to unmarshal, so any
// existing data in pb is always removed. Use UnmarshalMerge
// to preserve and append to existing data.
func Unmarshal(buf []byte, pb Message) error {
	pb.Reset()
	if u, ok := pb.(newUnmarshaler); ok {
		return u.XXX_Unmarshal(buf)
	}
	if u, ok := pb.(Unmarshaler); ok {
		return u.Unmarshal(buf)
	}
	return NewBuffer(buf).Unmarshal(pb)
}

// UnmarshalMerge parses the protocol buffer representation in buf and
// writes the decoded result to pb.  If the struct underlying pb does not match
// the data in buf, the results can be unpredictable.
//
// UnmarshalMerge merges into existing data in pb.
// Most code should use Unmarshal instead.
func UnmarshalMerge(buf []byte, pb Message) error {
	if u, ok := pb.(newUnmarshaler); ok {
		return u.XXX_Unmarshal(buf)
	}
	if u, ok := pb.(Unmarshaler); ok {
		// NOTE: The history of proto have unfortunately been inconsistent
		// whether Unmarshaler should or should not implicitly clear itself.
		// Some implementations do, most do not.
		// Thus, calling this here may or may not do what people want.
		//
		// See https://github.com/golang/protobuf/issues/424
		return u.Unmarshal(buf)
	}
	return NewBuffer(buf).Unmarshal(pb)
}

// DecodeMessage reads a count-delimited message from the Buffer.
func (p *Buffer) DecodeMessage(pb Message) error {
	enc, err := p.DecodeRawBytes(false)
	if err != nil {
		return err
	}
	return NewBuffer(enc).Unmarshal(pb)
}

// DecodeGroup reads a tag-delimited group from the Buffer.
// StartGroup tag is already consumed. This function consumes
// EndGroup tag.
func (p *Buffer) DecodeGroup(pb Message) error {
	b := p.buf[p.index:]
	x, y := findEndGroup(b)
	if x < 0 {
		return io.ErrUnexpectedEOF
	}
	err := Unmarshal(b[:x], pb)
	p.index += y
	return err
}

// Unmarshal parses the protocol buffer representation in the
// Buffer and places the decoded result in pb.  If the struct
// underlying pb does not match the data in the buffer, the results can be
// unpredictable.
//
// Unlike proto.Unmarshal, this does not reset pb before starting to unmarshal.
func (p *Buffer) Unmarshal(pb Message) error {
	// If the object can unmarshal itself, let it.
	if u, ok := pb.(newUnmarshaler); ok {
		err := u.XXX_Unmarshal(p.buf[p.index:])
		p.index = len(p.buf)
		return err
	}
	if u, ok := pb.(Unmarshaler); ok {
		// NOTE: The history of proto have unfortunately been inconsistent
		// whether Unmarshaler should or should not implicitly clear itself.
		// Some implementations do, most do not.
		// Thus, calling this here may or may not do what people want.
		//
		// See https://github.com/golang/protobuf/issues/424
		err := u.Unmarshal(p.buf[p.index:])
		p.index = len(p.buf)
		return err
	}

	// Slow workaround for messages that aren't Unmarshalers.
	// This includes some hand-coded .pb.go files and
	// bootstrap protos.
	// TODO: fix all of those and then add Unmarshal to
	// the Message interface. Then:
	// The cast above and code below can be deleted.
	// The old unmarshaler can be deleted.
	// Clients can call Unmarshal directly (can already do that, actually).
	var info InternalMessageInfo
	err := info.Unmarshal(pb, p.buf[p.index:])
	p.index = len(p.buf)
	return err
}