原理

bufio通过缓冲提高效率

把文件读取进缓冲(内存)避免每次读取触发系统io

1
2
3
4
5
6
7
participant 程序 as A
participant 缓冲区buf as B
participant 文件 as C
B--A:写入内容小于buf
B--A:
C--B:buf没空间,写入文件,清空buf
C--A:写入内容大于buf

把文件写入缓冲,多次写入后,最后一次性写入文件·

1
2
3
4
5
程序--缓冲区buf:写入内容小于buf
程序--缓冲区buf:
缓冲区buf--文件:buf没空间,写入文件,清空buf
程序--文件:写入内容大于buf

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
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
// 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 bufio implements buffered I/O. It wraps an io.Reader or io.Writer
// object, creating another object (Reader or Writer) that also implements
// the interface but provides buffering and some help for textual I/O.
package bufio

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

const (
defaultBufSize = 4096
)

var (
ErrInvalidUnreadByte = errors.New("bufio: invalid use of UnreadByte")
ErrInvalidUnreadRune = errors.New("bufio: invalid use of UnreadRune")
ErrBufferFull = errors.New("bufio: buffer full")
ErrNegativeCount = errors.New("bufio: negative count")
)

// Buffered input.

// Reader implements buffering for an io.Reader object.对io.Reader的封装
type Reader struct {
buf []byte
rd io.Reader // reader provided by the client
r, w int // buf read and write positions
err error
lastByte int // last byte read for UnreadByte; -1 means invalid
lastRuneSize int // size of last rune read for UnreadRune; -1 means invalid
}

const minReadBufferSize = 16
const maxConsecutiveEmptyReads = 100

// NewReaderSize returns a new Reader whose buffer has at least the specified
// size. If the argument io.Reader is already a Reader with large enough
// size, it returns the underlying Reader.
func NewReaderSize(rd io.Reader, size int) *Reader {
// Is it already a Reader?
b, ok := rd.(*Reader)
if ok && len(b.buf) >= size {
return b
}
if size < minReadBufferSize {
size = minReadBufferSize
}
r := new(Reader)
r.reset(make([]byte, size), rd)
return r
}

// NewReader returns a new Reader whose buffer has the default size.
func NewReader(rd io.Reader) *Reader {
return NewReaderSize(rd, defaultBufSize)
}

// Size returns the size of the underlying buffer in bytes.
func (b *Reader) Size() int { return len(b.buf) }

// Reset discards any buffered data, resets all state, and switches
// the buffered reader to read from r.
func (b *Reader) Reset(r io.Reader) {
b.reset(b.buf, r)
}

func (b *Reader) reset(buf []byte, r io.Reader) {
*b = Reader{
buf: buf,
rd: r,
lastByte: -1,
lastRuneSize: -1,
}
}

var errNegativeRead = errors.New("bufio: reader returned negative count from Read")

// fill reads a new chunk into the buffer.
func (b *Reader) fill() {
// Slide existing data to beginning.
if b.r > 0 {
copy(b.buf, b.buf[b.r:b.w])
b.w -= b.r
b.r = 0
}

if b.w >= len(b.buf) {
panic("bufio: tried to fill full buffer")
}

// Read new data: try a limited number of times.
for i := maxConsecutiveEmptyReads; i > 0; i-- {
n, err := b.rd.Read(b.buf[b.w:])
if n < 0 {
panic(errNegativeRead)
}
b.w += n
if err != nil {
b.err = err
return
}
if n > 0 {
return
}
}
b.err = io.ErrNoProgress
}

func (b *Reader) readErr() error {
err := b.err
b.err = nil
return err
}

// Peek returns the next n bytes without advancing the reader. The bytes stop
// being valid at the next read call. If Peek returns fewer than n bytes, it
// also returns an error explaining why the read is short. The error is
// ErrBufferFull if n is larger than b's buffer size.
//
// Calling Peek prevents a UnreadByte or UnreadRune call from succeeding
// until the next read operation.
func (b *Reader) Peek(n int) ([]byte, error) {
if n < 0 {
return nil, ErrNegativeCount
}

b.lastByte = -1
b.lastRuneSize = -1

for b.w-b.r < n && b.w-b.r < len(b.buf) && b.err == nil {
b.fill() // b.w-b.r < len(b.buf) => buffer is not full
}

if n > len(b.buf) {
return b.buf[b.r:b.w], ErrBufferFull
}

// 0 <= n <= len(b.buf)
var err error
if avail := b.w - b.r; avail < n {
// not enough data in buffer
n = avail
err = b.readErr()
if err == nil {
err = ErrBufferFull
}
}
return b.buf[b.r : b.r+n], err
}

// Discard skips the next n bytes, returning the number of bytes discarded.
//
// If Discard skips fewer than n bytes, it also returns an error.
// If 0 <= n <= b.Buffered(), Discard is guaranteed to succeed without
// reading from the underlying io.Reader.
func (b *Reader) Discard(n int) (discarded int, err error) {
if n < 0 {
return 0, ErrNegativeCount
}
if n == 0 {
return
}
remain := n
for {
skip := b.Buffered()
if skip == 0 {
b.fill()
skip = b.Buffered()
}
if skip > remain {
skip = remain
}
b.r += skip
remain -= skip
if remain == 0 {
return n, nil
}
if b.err != nil {
return n - remain, b.readErr()
}
}
}

// Read reads data into p.
// It returns the number of bytes read into p.
// The bytes are taken from at most one Read on the underlying Reader,
// hence n may be less than len(p).
// To read exactly len(p) bytes, use io.ReadFull(b, p).
// At EOF, the count will be zero and err will be io.EOF.
func (b *Reader) Read(p []byte) (n int, err error) {
n = len(p)
if n == 0 {
if b.Buffered() > 0 {
return 0, nil
}
return 0, b.readErr()
}
if b.r == b.w {
if b.err != nil {
return 0, b.readErr()
}
if len(p) >= len(b.buf) {
// Large read, empty buffer.
// Read directly into p to avoid copy.
n, b.err = b.rd.Read(p)
if n < 0 {
panic(errNegativeRead)
}
if n > 0 {
b.lastByte = int(p[n-1])
b.lastRuneSize = -1
}
return n, b.readErr()
}
// One read.
// Do not use b.fill, which will loop.
b.r = 0
b.w = 0
n, b.err = b.rd.Read(b.buf)
if n < 0 {
panic(errNegativeRead)
}
if n == 0 {
return 0, b.readErr()
}
b.w += n
}

// copy as much as we can
n = copy(p, b.buf[b.r:b.w])
b.r += n
b.lastByte = int(b.buf[b.r-1])
b.lastRuneSize = -1
return n, nil
}

// ReadByte reads and returns a single byte.
// If no byte is available, returns an error.
func (b *Reader) ReadByte() (byte, error) {
b.lastRuneSize = -1
for b.r == b.w {
if b.err != nil {
return 0, b.readErr()
}
b.fill() // buffer is empty
}
c := b.buf[b.r]
b.r++
b.lastByte = int(c)
return c, nil
}

// UnreadByte unreads the last byte. Only the most recently read byte can be unread.
//
// UnreadByte returns an error if the most recent method called on the
// Reader was not a read operation. Notably, Peek is not considered a
// read operation.
func (b *Reader) UnreadByte() error {
if b.lastByte < 0 || b.r == 0 && b.w > 0 {
return ErrInvalidUnreadByte
}
// b.r > 0 || b.w == 0
if b.r > 0 {
b.r--
} else {
// b.r == 0 && b.w == 0
b.w = 1
}
b.buf[b.r] = byte(b.lastByte)
b.lastByte = -1
b.lastRuneSize = -1
return nil
}

// ReadRune reads a single UTF-8 encoded Unicode character and returns the
// rune and its size in bytes. If the encoded rune is invalid, it consumes one byte
// and returns unicode.ReplacementChar (U+FFFD) with a size of 1.
func (b *Reader) ReadRune() (r rune, size int, err error) {
for b.r+utf8.UTFMax > b.w && !utf8.FullRune(b.buf[b.r:b.w]) && b.err == nil && b.w-b.r < len(b.buf) {
b.fill() // b.w-b.r < len(buf) => buffer is not full
}
b.lastRuneSize = -1
if b.r == b.w {
return 0, 0, b.readErr()
}
r, size = rune(b.buf[b.r]), 1
if r >= utf8.RuneSelf {
r, size = utf8.DecodeRune(b.buf[b.r:b.w])
}
b.r += size
b.lastByte = int(b.buf[b.r-1])
b.lastRuneSize = size
return r, size, nil
}

// UnreadRune unreads the last rune. If the most recent method called on
// the Reader 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 *Reader) UnreadRune() error {
if b.lastRuneSize < 0 || b.r < b.lastRuneSize {
return ErrInvalidUnreadRune
}
b.r -= b.lastRuneSize
b.lastByte = -1
b.lastRuneSize = -1
return nil
}

// Buffered returns the number of bytes that can be read from the current buffer.
func (b *Reader) Buffered() int { return b.w - b.r }

// ReadSlice reads until the first occurrence of delim in the input,
// returning a slice pointing at the bytes in the buffer.
// The bytes stop being valid at the next read.
// If ReadSlice encounters an error before finding a delimiter,
// it returns all the data in the buffer and the error itself (often io.EOF).
// ReadSlice fails with error ErrBufferFull if the buffer fills without a delim.
// Because the data returned from ReadSlice will be overwritten
// by the next I/O operation, most clients should use
// ReadBytes or ReadString instead.
// ReadSlice returns err != nil if and only if line does not end in delim.
func (b *Reader) ReadSlice(delim byte) (line []byte, err error) {
s := 0 // search start index
for {
// Search buffer.
if i := bytes.IndexByte(b.buf[b.r+s:b.w], delim); i >= 0 {
i += s
line = b.buf[b.r : b.r+i+1]
b.r += i + 1
break
}

// Pending error?
if b.err != nil {
line = b.buf[b.r:b.w]
b.r = b.w
err = b.readErr()
break
}

// Buffer full?
if b.Buffered() >= len(b.buf) {
b.r = b.w
line = b.buf
err = ErrBufferFull
break
}

s = b.w - b.r // do not rescan area we scanned before

b.fill() // buffer is not full
}

// Handle last byte, if any.
if i := len(line) - 1; i >= 0 {
b.lastByte = int(line[i])
b.lastRuneSize = -1
}

return
}

// ReadLine is a low-level line-reading primitive. Most callers should use
// ReadBytes('\n') or ReadString('\n') instead or use a Scanner.
//
// ReadLine tries to return a single line, not including the end-of-line bytes.
// If the line was too long for the buffer then isPrefix is set and the
// beginning of the line is returned. The rest of the line will be returned
// from future calls. isPrefix will be false when returning the last fragment
// of the line. The returned buffer is only valid until the next call to
// ReadLine. ReadLine either returns a non-nil line or it returns an error,
// never both.
//
// The text returned from ReadLine does not include the line end ("\r\n" or "\n").
// No indication or error is given if the input ends without a final line end.
// Calling UnreadByte after ReadLine will always unread the last byte read
// (possibly a character belonging to the line end) even if that byte is not
// part of the line returned by ReadLine.
func (b *Reader) ReadLine() (line []byte, isPrefix bool, err error) {
line, err = b.ReadSlice('\n')
if err == ErrBufferFull {
// Handle the case where "\r\n" straddles the buffer.
if len(line) > 0 && line[len(line)-1] == '\r' {
// Put the '\r' back on buf and drop it from line.
// Let the next call to ReadLine check for "\r\n".
if b.r == 0 {
// should be unreachable
panic("bufio: tried to rewind past start of buffer")
}
b.r--
line = line[:len(line)-1]
}
return line, true, nil
}

if len(line) == 0 {
if err != nil {
line = nil
}
return
}
err = nil

if line[len(line)-1] == '\n' {
drop := 1
if len(line) > 1 && line[len(line)-2] == '\r' {
drop = 2
}
line = line[:len(line)-drop]
}
return
}

// 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.
// For simple uses, a Scanner may be more convenient.
func (b *Reader) ReadBytes(delim byte) ([]byte, error) {
// Use ReadSlice to look for array,
// accumulating full buffers.
var frag []byte
var full [][]byte
var err error
for {
var e error
frag, e = b.ReadSlice(delim)
if e == nil { // got final fragment
break
}
if e != ErrBufferFull { // unexpected error
err = e
break
}

// Make a copy of the buffer.
buf := make([]byte, len(frag))
copy(buf, frag)
full = append(full, buf)
}

// Allocate new buffer to hold the full pieces and the fragment.
n := 0
for i := range full {
n += len(full[i])
}
n += len(frag)

// Copy full pieces and fragment in.
buf := make([]byte, n)
n = 0
for i := range full {
n += copy(buf[n:], full[i])
}
copy(buf[n:], frag)
return buf, 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.
// For simple uses, a Scanner may be more convenient.
func (b *Reader) ReadString(delim byte) (string, error) {
bytes, err := b.ReadBytes(delim)
return string(bytes), err
}

// WriteTo implements io.WriterTo.
// This may make multiple calls to the Read method of the underlying Reader.
// If the underlying reader supports the WriteTo method,
// this calls the underlying WriteTo without buffering.
func (b *Reader) WriteTo(w io.Writer) (n int64, err error) {
n, err = b.writeBuf(w)
if err != nil {
return
}

if r, ok := b.rd.(io.WriterTo); ok {
m, err := r.WriteTo(w)
n += m
return n, err
}

if w, ok := w.(io.ReaderFrom); ok {
m, err := w.ReadFrom(b.rd)
n += m
return n, err
}

if b.w-b.r < len(b.buf) {
b.fill() // buffer not full
}

for b.r < b.w {
// b.r < b.w => buffer is not empty
m, err := b.writeBuf(w)
n += m
if err != nil {
return n, err
}
b.fill() // buffer is empty
}

if b.err == io.EOF {
b.err = nil
}

return n, b.readErr()
}

var errNegativeWrite = errors.New("bufio: writer returned negative count from Write")

// writeBuf writes the Reader's buffer to the writer.
func (b *Reader) writeBuf(w io.Writer) (int64, error) {
n, err := w.Write(b.buf[b.r:b.w])
if n < 0 {
panic(errNegativeWrite)
}
b.r += n
return int64(n), err
}

// buffered output

// Writer implements buffering for an io.Writer object.
// If an error occurs writing to a Writer, no more data will be
// accepted and all subsequent writes, and Flush, will return the error.
// After all data has been written, the client should call the
// Flush method to guarantee all data has been forwarded to
// the underlying io.Writer.
type Writer struct {
err error
buf []byte
n int
wr io.Writer
}

// NewWriterSize returns a new Writer whose buffer has at least the specified
// size. If the argument io.Writer is already a Writer with large enough
// size, it returns the underlying Writer.
func NewWriterSize(w io.Writer, size int) *Writer {
// Is it already a Writer?
b, ok := w.(*Writer)
if ok && len(b.buf) >= size {
return b
}
if size <= 0 {
size = defaultBufSize
}
return &Writer{
buf: make([]byte, size),
wr: w,
}
}

// NewWriter returns a new Writer whose buffer has the default size.
func NewWriter(w io.Writer) *Writer {
return NewWriterSize(w, defaultBufSize)
}

// Size returns the size of the underlying buffer in bytes.
func (b *Writer) Size() int { return len(b.buf) }

// Reset discards any unflushed buffered data, clears any error, and
// resets b to write its output to w.
func (b *Writer) Reset(w io.Writer) {
b.err = nil
b.n = 0
b.wr = w
}

// Flush writes any buffered data to the underlying io.Writer.
func (b *Writer) Flush() error {
if b.err != nil {
return b.err
}
if b.n == 0 {
return nil
}
n, err := b.wr.Write(b.buf[0:b.n])
if n < b.n && err == nil {
err = io.ErrShortWrite
}
if err != nil {
if n > 0 && n < b.n {
copy(b.buf[0:b.n-n], b.buf[n:b.n])
}
b.n -= n
b.err = err
return err
}
b.n = 0
return nil
}

// Available returns how many bytes are unused in the buffer.
func (b *Writer) Available() int { return len(b.buf) - b.n }

// Buffered returns the number of bytes that have been written into the current buffer.
func (b *Writer) Buffered() int { return b.n }

// Write writes the contents of p into the buffer.
// It returns the number of bytes written.
// If nn < len(p), it also returns an error explaining
// why the write is short.
func (b *Writer) Write(p []byte) (nn int, err error) {
for len(p) > b.Available() && b.err == nil {
var n int
if b.Buffered() == 0 {
// Large write, empty buffer.
// Write directly from p to avoid copy.
n, b.err = b.wr.Write(p)
} else {
n = copy(b.buf[b.n:], p)
b.n += n
b.Flush()
}
nn += n
p = p[n:]
}
if b.err != nil {
return nn, b.err
}
n := copy(b.buf[b.n:], p)
b.n += n
nn += n
return nn, nil
}

// WriteByte writes a single byte.
func (b *Writer) WriteByte(c byte) error {
if b.err != nil {
return b.err
}
if b.Available() <= 0 && b.Flush() != nil {
return b.err
}
b.buf[b.n] = c
b.n++
return nil
}

// WriteRune writes a single Unicode code point, returning
// the number of bytes written and any error.
func (b *Writer) WriteRune(r rune) (size int, err error) {
if r < utf8.RuneSelf {
err = b.WriteByte(byte(r))
if err != nil {
return 0, err
}
return 1, nil
}
if b.err != nil {
return 0, b.err
}
n := b.Available()
if n < utf8.UTFMax {
if b.Flush(); b.err != nil {
return 0, b.err
}
n = b.Available()
if n < utf8.UTFMax {
// Can only happen if buffer is silly small.
return b.WriteString(string(r))
}
}
size = utf8.EncodeRune(b.buf[b.n:], r)
b.n += size
return size, nil
}

// WriteString writes a string.
// It returns the number of bytes written.
// If the count is less than len(s), it also returns an error explaining
// why the write is short.
func (b *Writer) WriteString(s string) (int, error) {
nn := 0
for len(s) > b.Available() && b.err == nil {
n := copy(b.buf[b.n:], s)
b.n += n
nn += n
s = s[n:]
b.Flush()
}
if b.err != nil {
return nn, b.err
}
n := copy(b.buf[b.n:], s)
b.n += n
nn += n
return nn, nil
}

// ReadFrom implements io.ReaderFrom. If the underlying writer
// supports the ReadFrom method, and b has no buffered data yet,
// this calls the underlying ReadFrom without buffering.
func (b *Writer) ReadFrom(r io.Reader) (n int64, err error) {
if b.Buffered() == 0 {
if w, ok := b.wr.(io.ReaderFrom); ok {
return w.ReadFrom(r)
}
}
var m int
for {
if b.Available() == 0 {
if err1 := b.Flush(); err1 != nil {
return n, err1
}
}
nr := 0
for nr < maxConsecutiveEmptyReads {
m, err = r.Read(b.buf[b.n:])
if m != 0 || err != nil {
break
}
nr++
}
if nr == maxConsecutiveEmptyReads {
return n, io.ErrNoProgress
}
b.n += m
n += int64(m)
if err != nil {
break
}
}
if err == io.EOF {
// If we filled the buffer exactly, flush preemptively.
if b.Available() == 0 {
err = b.Flush()
} else {
err = nil
}
}
return n, err
}

// buffered input and output

// ReadWriter stores pointers to a Reader and a Writer.
// It implements io.ReadWriter.
type ReadWriter struct {
*Reader
*Writer
}

// NewReadWriter allocates a new ReadWriter that dispatches to r and w.
func NewReadWriter(r *Reader, w *Writer) *ReadWriter {
return &ReadWriter{r, w}
}