我们在日常开发中经常要用到字符串拼接,Golang提供了多种拼接方法。常用有以下几种:
- “+” operator
- fmt.Sprintf
- bytes.Buffer
- strings.Builder
一,Benchmark 比较
下表是在VMware VM(centos7)上做的测试,拼接一个字符串包含1000个字符x。
BenchmarkSimple-2 7265664 164 ns/op 530 B/op 0 allocs/op
BenchmarkSprintf-2 4183986 298 ns/op 546 B/op 1 allocs/op
BenchmarkBytesBuffer-2 90349341 11.9 ns/op 2 B/op 0 allocs/op
BenchmarkStringBuilder-2 370823845 3.23 ns/op 2 B/op 0 allocs/op
我们可以得出以下结果:
从数量级上看,bytes.Buffer (BenchmarkBytesBuffer-2) 和 strings.Builder (BenchmarkStringBuilder-2) 要优于 “+” operator (BenchmarkSimple-2) 和 fmt.Sprintf (BenchmarkSprintf-2)
细微上看,strings.Builder (BenchmarkStringBuilder-2) 优于 bytes.Buffer (BenchmarkBytesBuffer-2)。“+” operator (BenchmarkSimple-2) 优于 fmt.Sprintf (BenchmarkSprintf-2)。
对待一些简单得场景,“+” operator足够好用。而一些复杂字符串的拼接,strings.Builder 完全可以替代 fmt.Sprintf,提高性能。
二,bytes.Buffer
有时候我们不仅仅是拼接字符串,而是字节“串”,例如文件IO,网络IO等。bytes.Buffer 绝对是一个最佳选择,提供丰富易用的函数集。
主要的数据结构:
// A Buffer is a variable-sized buffer of bytes with Read and Write methods.
// The zero value for Buffer is an empty buffer ready to use.
type Buffer struct {
buf []byte // contents are the bytes buf[off : len(buf)]
off int // read at &buf[off], write at &buf[len(buf)]
lastRead readOp // last read operation, so that Unread* can work correctly.
}
建立新 Buffer - 没有初始值
new(bytes.Buffer)
建立新 Buffer - 有初始值
// NewBuffer creates and initializes a new Buffer using buf as its
// initial contents. The new Buffer takes ownership of buf, and the
// caller should not use buf after this call. NewBuffer is intended to
// prepare a Buffer to read existing data. It can also be used to set
// the initial size of the internal buffer for writing. To do that,
// buf should have the desired capacity but a length of zero.
//
// In most cases, new(Buffer) (or just declaring a Buffer variable) is
// sufficient to initialize a Buffer.
func NewBuffer(buf []byte) *Buffer { return &Buffer{buf: buf} }
// NewBufferString creates and initializes a new Buffer using string s as its
// initial contents. It is intended to prepare a buffer to read an existing
// string.
//
// In most cases, new(Buffer) (or just declaring a Buffer variable) is
// sufficient to initialize a Buffer.
func NewBufferString(s string) *Buffer {
return &Buffer{buf: []byte(s)}
}
写 Buffer
// Write appends the contents of p to the buffer, growing the buffer as
// needed. The return value n is the length of p; err is always nil. If the
// buffer becomes too large, Write will panic with ErrTooLarge.
func (b *Buffer) Write(p []byte) (n int, err error) {
b.lastRead = opInvalid
m, ok := b.tryGrowByReslice(len(p))
if !ok {
m = b.grow(len(p))
}
return copy(b.buf[m:], p), nil
}
// WriteString appends the contents of s to the buffer, growing the buffer as
// needed. The return value n is the length of s; err is always nil. If the
// buffer becomes too large, WriteString will panic with ErrTooLarge.
func (b *Buffer) WriteString(s string) (n int, err error) {
b.lastRead = opInvalid
m, ok := b.tryGrowByReslice(len(s))
if !ok {
m = b.grow(len(s))
}
return copy(b.buf[m:], s), nil
}
// WriteByte appends the byte c to the buffer, growing the buffer as needed.
// The returned error is always nil, but is included to match bufio.Writer's
// WriteByte. If the buffer becomes too large, WriteByte will panic with
// ErrTooLarge.
func (b *Buffer) WriteByte(c byte) error {
b.lastRead = opInvalid
m, ok := b.tryGrowByReslice(1)
if !ok {
m = b.grow(1)
}
b.buf[m] = c
return nil
}
// WriteRune appends the UTF-8 encoding of Unicode code point r to the
// buffer, returning its length and an error, which is always nil but is
// included to match bufio.Writer's WriteRune. The buffer is grown as needed;
// if it becomes too large, WriteRune will panic with ErrTooLarge.
func (b *Buffer) WriteRune(r rune) (n int, err error) {
if r < utf8.RuneSelf {
b.WriteByte(byte(r))
return 1, nil
}
b.lastRead = opInvalid
m, ok := b.tryGrowByReslice(utf8.UTFMax)
if !ok {
m = b.grow(utf8.UTFMax)
}
n = utf8.EncodeRune(b.buf[m:m+utf8.UTFMax], r)
b.buf = b.buf[:m+n]
return n, nil
}
// WriteTo writes data to w until the buffer is drained or an error occurs.
// The return value n is the number of bytes written; it always fits into an
// int, but it is int64 to match the io.WriterTo interface. Any error
// encountered during the write is also returned.
func (b *Buffer) WriteTo(w io.Writer) (n int64, err error) {
b.lastRead = opInvalid
if nBytes := b.Len(); nBytes > 0 {
m, e := w.Write(b.buf[b.off:])
if m > nBytes {
panic("bytes.Buffer.WriteTo: invalid Write count")
}
b.off += m
n = int64(m)
if e != nil {
return n, e
}
// all bytes should have been written, by definition of
// Write method in io.Writer
if m != nBytes {
return n, io.ErrShortWrite
}
}
// Buffer is now empty; reset.
b.Reset()
return n, nil
}
读 Buffer
// Read reads the next len(p) bytes from the buffer or until the buffer
// is drained. The return value n is the number of bytes read. If the
// buffer has no data to return, err is io.EOF (unless len(p) is zero);
// otherwise it is nil.
func (b *Buffer) Read(p []byte) (n int, err error) {
b.lastRead = opInvalid
if b.empty() {
// Buffer is empty, reset to recover space.
b.Reset()
if len(p) == 0 {
return 0, nil
}
return 0, io.EOF
}
n = copy(p, b.buf[b.off:])
b.off += n
if n > 0 {
b.lastRead = opRead
}
return n, nil
}
// Next returns a slice containing the next n bytes from the buffer,
// advancing the buffer as if the bytes had been returned by Read.
// If there are fewer than n bytes in the buffer, Next returns the entire buffer.
// The slice is only valid until the next call to a read or write method.
func (b *Buffer) Next(n int) []byte {
b.lastRead = opInvalid
m := b.Len()
if n > m {
n = m
}
data := b.buf[b.off : b.off+n]
b.off += n
if n > 0 {
b.lastRead = opRead
}
return data
}
// ReadByte reads and returns the next byte from the buffer.
// If no byte is available, it returns error io.EOF.
func (b *Buffer) ReadByte() (byte, error) {
if b.empty() {
// Buffer is empty, reset to recover space.
b.Reset()
return 0, io.EOF
}
c := b.buf[b.off]
b.off++
b.lastRead = opRead
return c, nil
}
// ReadRune reads and returns the next UTF-8-encoded
// Unicode code point from the buffer.
// If no bytes are available, the error returned is io.EOF.
// If the bytes are an erroneous UTF-8 encoding, it
// consumes one byte and returns U+FFFD, 1.
func (b *Buffer) ReadRune() (r rune, size int, err error) {
if b.empty() {
// Buffer is empty, reset to recover space.
b.Reset()
return 0, 0, io.EOF
}
c := b.buf[b.off]
if c < utf8.RuneSelf {
b.off++
b.lastRead = opReadRune1
return rune(c), 1, nil
}
r, n := utf8.DecodeRune(b.buf[b.off:])
b.off += n
b.lastRead = readOp(n)
return r, n, nil
}
// UnreadRune unreads the last rune returned by ReadRune.
// If the most recent read or write operation on the buffer was
// not a successful ReadRune, UnreadRune returns an error. (In this regard
// it is stricter than UnreadByte, which will unread the last byte
// from any read operation.)
func (b *Buffer) UnreadRune() error {
if b.lastRead <= opInvalid {
return errors.New("bytes.Buffer: UnreadRune: previous operation was not a successful ReadRune")
}
if b.off >= int(b.lastRead) {
b.off -= int(b.lastRead)
}
b.lastRead = opInvalid
return nil
}
var errUnreadByte = errors.New("bytes.Buffer: UnreadByte: previous operation was not a successful read")
// UnreadByte unreads the last byte returned by the most recent successful
// read operation that read at least one byte. If a write has happened since
// the last read, if the last read returned an error, or if the read read zero
// bytes, UnreadByte returns an error.
func (b *Buffer) UnreadByte() error {
if b.lastRead == opInvalid {
return errUnreadByte
}
b.lastRead = opInvalid
if b.off > 0 {
b.off--
}
return nil
}
// ReadBytes reads until the first occurrence of delim in the input,
// returning a slice containing the data up to and including the delimiter.
// If ReadBytes encounters an error before finding a delimiter,
// it returns the data read before the error and the error itself (often io.EOF).
// ReadBytes returns err != nil if and only if the returned data does not end in
// delim.
func (b *Buffer) ReadBytes(delim byte) (line []byte, err error) {
slice, err := b.readSlice(delim)
// return a copy of slice. The buffer's backing array may
// be overwritten by later calls.
line = append(line, slice...)
return line, err
}
// ReadString reads until the first occurrence of delim in the input,
// returning a string containing the data up to and including the delimiter.
// If ReadString encounters an error before finding a delimiter,
// it returns the data read before the error and the error itself (often io.EOF).
// ReadString returns err != nil if and only if the returned data does not end
// in delim.
func (b *Buffer) ReadString(delim byte) (line string, err error) {
slice, err := b.readSlice(delim)
return string(slice), err
}
置零 Buffer
// Reset resets the buffer to be empty,
// but it retains the underlying storage for use by future writes.
// Reset is the same as Truncate(0).
func (b *Buffer) Reset() {
b.buf = b.buf[:0]
b.off = 0
b.lastRead = opInvalid
}
导出 Buffer
// Bytes returns a slice of length b.Len() holding the unread portion of the buffer.
// The slice is valid for use only until the next buffer modification (that is,
// only until the next call to a method like Read, Write, Reset, or Truncate).
// The slice aliases the buffer content at least until the next buffer modification,
// so immediate changes to the slice will affect the result of future reads.
func (b *Buffer) Bytes() []byte { return b.buf[b.off:] }
// String returns the contents of the unread portion of the buffer
// as a string. If the Buffer is a nil pointer, it returns "<nil>".
//
// To build strings more efficiently, see the strings.Builder type.
func (b *Buffer) String() string {
if b == nil {
// Special case, useful in debugging.
return "<nil>"
}
return string(b.buf[b.off:])
}
// Len returns the number of bytes of the unread portion of the buffer;
// b.Len() == len(b.Bytes()).
func (b *Buffer) Len() int { return len(b.buf) - b.off }
// Cap returns the capacity of the buffer's underlying byte slice, that is, the
// total space allocated for the buffer's data.
func (b *Buffer) Cap() int { return cap(b.buf) }
一个例子:来自以太坊 Discovery 中的 Packet Encode 代码。
// Encode encodes a discovery packet.
func Encode(priv *ecdsa.PrivateKey, req Packet) (packet, hash []byte, err error) {
b := new(bytes.Buffer)
b.Write(headSpace)
b.WriteByte(req.Kind())
if err := rlp.Encode(b, req); err != nil {
return nil, nil, err
}
packet = b.Bytes()
sig, err := crypto.Sign(crypto.Keccak256(packet[headSize:]), priv)
if err != nil {
return nil, nil, err
}
copy(packet[macSize:], sig)
// Add the hash to the front. Note: this doesn't protect the packet in any way.
hash = crypto.Keccak256(packet[macSize:])
copy(packet, hash)
return packet, hash, nil
}
参考链接: