buffer.go 13 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416
// Copyright 2009 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 bytes

// Simple byte buffer for marshaling data.

import (
	"errors"
	"io"
	"unicode/utf8"
)

// 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)]
	runeBytes [utf8.UTFMax]byte // avoid allocation of slice on each WriteByte or Rune
	bootstrap [64]byte          // memory to hold first slice; helps small buffers (Printf) avoid allocation.
	lastRead  readOp            // last read operation, so that Unread* can work correctly.
}

// The readOp constants describe the last action performed on
// the buffer, so that UnreadRune and UnreadByte can
// check for invalid usage.
type readOp int

const (
	opInvalid  readOp = iota // Non-read operation.
	opReadRune               // Read rune.
	opRead                   // Any other read operation.
)

// ErrTooLarge is passed to panic if memory cannot be allocated to store data in a buffer.
var ErrTooLarge = errors.New("bytes.Buffer: too large")

// Bytes returns a slice of the contents of the unread portion of the buffer;
// len(b.Bytes()) == b.Len().  If the caller changes the contents of the
// returned slice, the contents of the buffer will change provided there
// are no intervening method calls on the Buffer.
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>".
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) }

// Truncate discards all but the first n unread bytes from the buffer.
// It panics if n is negative or greater than the length of the buffer.
func (b *Buffer) Truncate(n int) {
	b.lastRead = opInvalid
	switch {
	case n < 0 || n > b.Len():
		panic("bytes.Buffer: truncation out of range")
	case n == 0:
		// Reuse buffer space.
		b.off = 0
	}
	b.buf = b.buf[0 : b.off+n]
}

// Reset resets the buffer so it has no content.
// b.Reset() is the same as b.Truncate(0).
func (b *Buffer) Reset() { b.Truncate(0) }

// grow grows the buffer to guarantee space for n more bytes.
// It returns the index where bytes should be written.
// If the buffer can't grow it will panic with ErrTooLarge.
func (b *Buffer) grow(n int) int {
	m := b.Len()
	// If buffer is empty, reset to recover space.
	if m == 0 && b.off != 0 {
		b.Truncate(0)
	}
	if len(b.buf)+n > cap(b.buf) {
		var buf []byte
		if b.buf == nil && n <= len(b.bootstrap) {
			buf = b.bootstrap[0:]
		} else if m+n <= cap(b.buf)/2 {
			// We can slide things down instead of allocating a new
			// slice. We only need m+n <= cap(b.buf) to slide, but
			// we instead let capacity get twice as large so we
			// don't spend all our time copying.
			copy(b.buf[:], b.buf[b.off:])
			buf = b.buf[:m]
		} else {
			// not enough space anywhere
			buf = makeSlice(2*cap(b.buf) + n)
			copy(buf, b.buf[b.off:])
		}
		b.buf = buf
		b.off = 0
	}
	b.buf = b.buf[0 : b.off+m+n]
	return b.off + m
}

// Grow grows the buffer's capacity, if necessary, to guarantee space for
// another n bytes. After Grow(n), at least n bytes can be written to the
// buffer without another allocation.
// If n is negative, Grow will panic.
// If the buffer can't grow it will panic with ErrTooLarge.
func (b *Buffer) Grow(n int) {
	if n < 0 {
		panic("bytes.Buffer.Grow: negative count")
	}
	m := b.grow(n)
	b.buf = b.buf[0:m]
}

// 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 := 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 := b.grow(len(s))
	return copy(b.buf[m:], s), nil
}

// MinRead is the minimum slice size passed to a Read call by
// Buffer.ReadFrom.  As long as the Buffer has at least MinRead bytes beyond
// what is required to hold the contents of r, ReadFrom will not grow the
// underlying buffer.
const MinRead = 512

// ReadFrom reads data from r until EOF and appends it to the buffer, growing
// the buffer as needed. The return value n is the number of bytes read. Any
// error except io.EOF encountered during the read is also returned. If the
// buffer becomes too large, ReadFrom will panic with ErrTooLarge.
func (b *Buffer) ReadFrom(r io.Reader) (n int64, err error) {
	b.lastRead = opInvalid
	// If buffer is empty, reset to recover space.
	if b.off >= len(b.buf) {
		b.Truncate(0)
	}
	for {
		if free := cap(b.buf) - len(b.buf); free < MinRead {
			// not enough space at end
			newBuf := b.buf
			if b.off+free < MinRead {
				// not enough space using beginning of buffer;
				// double buffer capacity
				newBuf = makeSlice(2*cap(b.buf) + MinRead)
			}
			copy(newBuf, b.buf[b.off:])
			b.buf = newBuf[:len(b.buf)-b.off]
			b.off = 0
		}
		m, e := r.Read(b.buf[len(b.buf):cap(b.buf)])
		b.buf = b.buf[0 : len(b.buf)+m]
		n += int64(m)
		if e == io.EOF {
			break
		}
		if e != nil {
			return n, e
		}
	}
	return n, nil // err is EOF, so return nil explicitly
}

// makeSlice allocates a slice of size n. If the allocation fails, it panics
// with ErrTooLarge.
func makeSlice(n int) []byte {
	// If the make fails, give a known error.
	defer func() {
		if recover() != nil {
			panic(ErrTooLarge)
		}
	}()
	return make([]byte, n)
}

// 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 b.off < len(b.buf) {
		nBytes := b.Len()
		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.Truncate(0)
	return
}

// 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 := 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
	}
	n = utf8.EncodeRune(b.runeBytes[0:], r)
	b.Write(b.runeBytes[0:n])
	return n, nil
}

// 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.off >= len(b.buf) {
		// Buffer is empty, reset to recover space.
		b.Truncate(0)
		if len(p) == 0 {
			return
		}
		return 0, io.EOF
	}
	n = copy(p, b.buf[b.off:])
	b.off += n
	if n > 0 {
		b.lastRead = opRead
	}
	return
}

// 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() (c byte, err error) {
	b.lastRead = opInvalid
	if b.off >= len(b.buf) {
		// Buffer is empty, reset to recover space.
		b.Truncate(0)
		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) {
	b.lastRead = opInvalid
	if b.off >= len(b.buf) {
		// Buffer is empty, reset to recover space.
		b.Truncate(0)
		return 0, 0, io.EOF
	}
	b.lastRead = opReadRune
	c := b.buf[b.off]
	if c < utf8.RuneSelf {
		b.off++
		return rune(c), 1, nil
	}
	r, n := utf8.DecodeRune(b.buf[b.off:])
	b.off += 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 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 != opReadRune {
		return errors.New("bytes.Buffer: UnreadRune: previous operation was not ReadRune")
	}
	b.lastRead = opInvalid
	if b.off > 0 {
		_, n := utf8.DecodeLastRune(b.buf[0:b.off])
		b.off -= n
	}
	return nil
}

// UnreadByte unreads the last byte returned by the most recent
// read operation.  If write has happened since the last read, UnreadByte
// returns an error.
func (b *Buffer) UnreadByte() error {
	if b.lastRead != opReadRune && b.lastRead != opRead {
		return errors.New("bytes.Buffer: UnreadByte: previous operation was not a read")
	}
	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
}

// readSlice is like ReadBytes but returns a reference to internal buffer data.
func (b *Buffer) readSlice(delim byte) (line []byte, err error) {
	i := IndexByte(b.buf[b.off:], delim)
	end := b.off + i + 1
	if i < 0 {
		end = len(b.buf)
		err = io.EOF
	}
	line = b.buf[b.off:end]
	b.off = end
	b.lastRead = opRead
	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
}

// NewBuffer creates and initializes a new Buffer using buf as its initial
// contents.  It is intended to prepare a Buffer to read existing data.  It
// can also be used to size 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)}
}