aboutsummaryrefslogtreecommitdiffstats
path: root/rlp/encode.go
blob: a0531af012da326092150c2f28c38632f6223a32 (plain) (blame)
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
// 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 (
    "fmt"
    "io"
    "math/big"
    "reflect"
    "sync"
)

var (
    // Common encoded values.
    // These are useful when implementing EncodeRLP.
    EmptyString = []byte{0x80}
    EmptyList   = []byte{0xC0}
)

// 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
}

// ListSize returns the encoded size of an RLP list with the given
// content size.
func ListSize(contentSize uint64) uint64 {
    return uint64(headsize(contentSize)) + contentSize
}

// Encode writes the RLP encoding of val to w. Note that Encode may
// perform many small writes in some cases. Consider making w
// buffered.
//
// Encode uses the following type-dependent encoding rules:
//
// If the type implements the Encoder interface, Encode calls
// EncodeRLP. This is true even for nil pointers, please see the
// documentation for Encoder.
//
// To encode a pointer, the value being pointed to is encoded. For nil
// pointers, Encode will encode the zero value of the type. A nil
// pointer to a struct type always encodes as an empty RLP list.
// A nil pointer to an array encodes as an empty list (or empty string
// if the array has element type byte).
//
// Struct values are encoded as an RLP list of all their encoded
// public fields. Recursive struct types are supported.
//
// To encode slices and arrays, the elements are encoded as an RLP
// list of the value's elements. Note that arrays and slices with
// element type uint8 or byte are always encoded as an RLP string.
//
// A Go string is encoded as an RLP string.
//
// An unsigned integer value is encoded as an RLP string. Zero always
// encodes as an empty RLP string. Encode also supports *big.Int.
//
// An interface value encodes as the value contained in the interface.
//
// Boolean values are not supported, nor are signed integers, floating
// point numbers, maps, channels and functions.
func Encode(w io.Writer, val interface{}) error {
    if outer, ok := w.(*encbuf); ok {
        // Encode was called by some type's EncodeRLP.
        // Avoid copying by writing to the outer encbuf directly.
        return outer.encode(val)
    }
    eb := encbufPool.Get().(*encbuf)
    defer encbufPool.Put(eb)
    eb.reset()
    if err := eb.encode(val); err != nil {
        return err
    }
    return eb.toWriter(w)
}

// EncodeBytes returns the RLP encoding of val.
// Please see the documentation of Encode for the encoding rules.
func EncodeToBytes(val interface{}) ([]byte, error) {
    eb := encbufPool.Get().(*encbuf)
    defer encbufPool.Put(eb)
    eb.reset()
    if err := eb.encode(val); err != nil {
        return nil, err
    }
    return eb.toBytes(), nil
}

// EncodeReader 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) {
    eb := encbufPool.Get().(*encbuf)
    eb.reset()
    if err := eb.encode(val); err != nil {
        return 0, nil, err
    }
    return eb.size(), &encReader{buf: eb}, nil
}

type encbuf struct {
    str     []byte      // string data, contains everything except list headers
    lheads  []*listhead // all list headers
    lhsize  int         // sum of sizes of all encoded list headers
    sizebuf []byte      // 9-byte auxiliary buffer for uint encoding
}

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
    } else {
        sizesize := putint(buf[1:], size)
        buf[0] = largetag + byte(sizesize)
        return sizesize + 1
    }
}

// encbufs are pooled.
var encbufPool = sync.Pool{
    New: func() interface{} { return &encbuf{sizebuf: make([]byte, 9)} },
}

func (w *encbuf) reset() {
    w.lhsize = 0
    if w.str != nil {
        w.str = w.str[:0]
    }
    if w.lheads != nil {
        w.lheads = w.lheads[:0]
    }
}

// encbuf implements io.Writer so it can be passed it into EncodeRLP.
func (w *encbuf) Write(b []byte) (int, error) {
    w.str = append(w.str, b...)
    return len(b), nil
}

func (w *encbuf) encode(val interface{}) error {
    rval := reflect.ValueOf(val)
    ti, err := cachedTypeInfo(rval.Type(), tags{})
    if err != nil {
        return err
    }
    return ti.writer(rval, w)
}

func (w *encbuf) encodeStringHeader(size int) {
    if size < 56 {
        w.str = append(w.str, 0x80+byte(size))
    } else {
        // TODO: encode to w.str directly
        sizesize := putint(w.sizebuf[1:], uint64(size))
        w.sizebuf[0] = 0xB7 + byte(sizesize)
        w.str = append(w.str, w.sizebuf[:sizesize+1]...)
    }
}

func (w *encbuf) encodeString(b []byte) {
    if len(b) == 1 && b[0] <= 0x7F {
        // fits single byte, no string header
        w.str = append(w.str, b[0])
    } else {
        w.encodeStringHeader(len(b))
        w.str = append(w.str, b...)
    }
}

func (w *encbuf) list() *listhead {
    lh := &listhead{offset: len(w.str), size: w.lhsize}
    w.lheads = append(w.lheads, lh)
    return lh
}

func (w *encbuf) listEnd(lh *listhead) {
    lh.size = w.size() - lh.offset - lh.size
    if lh.size < 56 {
        w.lhsize += 1 // length encoded into kind tag
    } else {
        w.lhsize += 1 + intsize(uint64(lh.size))
    }
}

func (w *encbuf) size() int {
    return len(w.str) + w.lhsize
}

func (w *encbuf) toBytes() []byte {
    out := make([]byte, w.size())
    strpos := 0
    pos := 0
    for _, head := range w.lheads {
        // write string data before header
        n := copy(out[pos:], w.str[strpos:head.offset])
        pos += n
        strpos += n
        // write the header
        enc := head.encode(out[pos:])
        pos += len(enc)
    }
    // copy string data after the last list header
    copy(out[pos:], w.str[strpos:])
    return out
}

func (w *encbuf) toWriter(out io.Writer) (err error) {
    strpos := 0
    for _, head := range w.lheads {
        // write string data before header
        if head.offset-strpos > 0 {
            n, err := out.Write(w.str[strpos:head.offset])
            strpos += n
            if err != nil {
                return err
            }
        }
        // write the header
        enc := head.encode(w.sizebuf)
        if _, err = out.Write(enc); err != nil {
            return err
        }
    }
    if strpos < len(w.str) {
        // write string data after the last list header
        _, err = out.Write(w.str[strpos:])
    }
    return err
}

// encReader is the io.Reader returned by EncodeToReader.
// It releases its encbuf at EOF.
type encReader struct {
    buf    *encbuf // the buffer we're reading from. this is nil when we're at EOF.
    lhpos  int     // index of list header that we're reading
    strpos int     // current position in string buffer
    piece  []byte  // next piece to be read
}

func (r *encReader) Read(b []byte) (n int, err error) {
    for {
        if r.piece = r.next(); r.piece == nil {
            // Put the encode buffer back into the pool at EOF when it
            // is first encountered. Subsequent calls still return EOF
            // as the error but the buffer is no longer valid.
            if r.buf != nil {
                encbufPool.Put(r.buf)
                r.buf = nil
            }
            return n, io.EOF
        }
        nn := copy(b[n:], r.piece)
        n += nn
        if nn < len(r.piece) {
            // piece didn't fit, see you next time.
            r.piece = r.piece[nn:]
            return n, nil
        }
        r.piece = nil
    }
    panic("not reached")
}

// next returns the next piece of data to be read.
// it returns nil at EOF.
func (r *encReader) next() []byte {
    switch {
    case r.buf == nil:
        return nil

    case r.piece != nil:
        // There is still data available for reading.
        return r.piece

    case r.lhpos < len(r.buf.lheads):
        // We're before the last list header.
        head := r.buf.lheads[r.lhpos]
        sizebefore := head.offset - r.strpos
        if sizebefore > 0 {
            // String data before header.
            p := r.buf.str[r.strpos:head.offset]
            r.strpos += sizebefore
            return p
        } else {
            r.lhpos++
            return head.encode(r.buf.sizebuf)
        }

    case r.strpos < len(r.buf.str):
        // String data at the end, after all list headers.
        p := r.buf.str[r.strpos:]
        r.strpos = len(r.buf.str)
        return p

    default:
        return nil
    }
}

var (
    encoderInterface = reflect.TypeOf(new(Encoder)).Elem()
    big0             = big.NewInt(0)
)

// makeWriter creates a writer function for the given type.
func makeWriter(typ reflect.Type) (writer, error) {
    kind := typ.Kind()
    switch {
    case typ.Implements(encoderInterface):
        return writeEncoder, nil
    case kind != reflect.Ptr && reflect.PtrTo(typ).Implements(encoderInterface):
        return writeEncoderNoPtr, nil
    case kind == reflect.Interface:
        return writeInterface, nil
    case typ.AssignableTo(reflect.PtrTo(bigInt)):
        return writeBigIntPtr, nil
    case typ.AssignableTo(bigInt):
        return writeBigIntNoPtr, 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 writeByteArray, nil
    case kind == reflect.Slice || kind == reflect.Array:
        return makeSliceWriter(typ)
    case kind == reflect.Struct:
        return makeStructWriter(typ)
    case kind == reflect.Ptr:
        return makePtrWriter(typ)
    default:
        return nil, fmt.Errorf("rlp: type %v is not RLP-serializable", typ)
    }
}

func isByte(typ reflect.Type) bool {
    return typ.Kind() == reflect.Uint8 && !typ.Implements(encoderInterface)
}

func writeUint(val reflect.Value, w *encbuf) error {
    i := val.Uint()
    if i == 0 {
        w.str = append(w.str, 0x80)
    } else if i < 128 {
        // fits single byte
        w.str = append(w.str, byte(i))
    } else {
        // TODO: encode int to w.str directly
        s := putint(w.sizebuf[1:], i)
        w.sizebuf[0] = 0x80 + byte(s)
        w.str = append(w.str, w.sizebuf[:s+1]...)
    }
    return nil
}

func writeBool(val reflect.Value, w *encbuf) error {
    if val.Bool() {
        w.str = append(w.str, 0x01)
    } else {
        w.str = append(w.str, 0x80)
    }
    return nil
}

func writeBigIntPtr(val reflect.Value, w *encbuf) error {
    ptr := val.Interface().(*big.Int)
    if ptr == nil {
        w.str = append(w.str, 0x80)
        return nil
    }
    return writeBigInt(ptr, w)
}

func writeBigIntNoPtr(val reflect.Value, w *encbuf) error {
    i := val.Interface().(big.Int)
    return writeBigInt(&i, w)
}

func writeBigInt(i *big.Int, w *encbuf) error {
    if cmp := i.Cmp(big0); cmp == -1 {
        return fmt.Errorf("rlp: cannot encode negative *big.Int")
    } else if cmp == 0 {
        w.str = append(w.str, 0x80)
    } else {
        w.encodeString(i.Bytes())
    }
    return nil
}

func writeBytes(val reflect.Value, w *encbuf) error {
    w.encodeString(val.Bytes())
    return nil
}

func writeByteArray(val reflect.Value, w *encbuf) error {
    if !val.CanAddr() {
        // Slice requires the value to be addressable.
        // Make it addressable by copying.
        copy := reflect.New(val.Type()).Elem()
        copy.Set(val)
        val = copy
    }
    size := val.Len()
    slice := val.Slice(0, size).Bytes()
    w.encodeString(slice)
    return nil
}

func writeString(val reflect.Value, w *encbuf) 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 writeEncoder(val reflect.Value, w *encbuf) error {
    return val.Interface().(Encoder).EncodeRLP(w)
}

// writeEncoderNoPtr handles non-pointer values that implement Encoder
// with a pointer receiver.
func writeEncoderNoPtr(val reflect.Value, w *encbuf) error {
    if !val.CanAddr() {
        // We can't get the address. It would be possible make the
        // value addressable by creating a shallow copy, but this
        // creates other problems so we're not doing it (yet).
        //
        // package json simply doesn't call MarshalJSON for cases like
        // this, 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: game over: unadressable value of type %v, EncodeRLP is pointer method", val.Type())
    }
    return val.Addr().Interface().(Encoder).EncodeRLP(w)
}

func writeInterface(val reflect.Value, w *encbuf) 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()
    ti, err := cachedTypeInfo(eval.Type(), tags{})
    if err != nil {
        return err
    }
    return ti.writer(eval, w)
}

func makeSliceWriter(typ reflect.Type) (writer, error) {
    etypeinfo, err := cachedTypeInfo1(typ.Elem(), tags{})
    if err != nil {
        return nil, err
    }
    writer := func(val reflect.Value, w *encbuf) error {
        lh := w.list()
        vlen := val.Len()
        for i := 0; i < vlen; i++ {
            if err := etypeinfo.writer(val.Index(i), w); err != nil {
                return err
            }
        }
        w.listEnd(lh)
        return nil
    }
    return writer, nil
}

func makeStructWriter(typ reflect.Type) (writer, error) {
    fields, err := structFields(typ)
    if err != nil {
        return nil, err
    }
    writer := func(val reflect.Value, w *encbuf) 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
    }
    return writer, nil
}

func makePtrWriter(typ reflect.Type) (writer, error) {
    etypeinfo, err := cachedTypeInfo1(typ.Elem(), tags{})
    if err != nil {
        return nil, err
    }

    // determine nil pointer handler
    var nilfunc func(*encbuf) error
    kind := typ.Elem().Kind()
    switch {
    case kind == reflect.Array && isByte(typ.Elem().Elem()):
        nilfunc = func(w *encbuf) error {
            w.str = append(w.str, 0x80)
            return nil
        }
    case kind == reflect.Struct || kind == reflect.Array:
        nilfunc = func(w *encbuf) error {
            // encoding the zero value of a struct/array could trigger
            // infinite recursion, avoid that.
            w.listEnd(w.list())
            return nil
        }
    default:
        zero := reflect.Zero(typ.Elem())
        nilfunc = func(w *encbuf) error {
            return etypeinfo.writer(zero, w)
        }
    }

    writer := func(val reflect.Value, w *encbuf) error {
        if val.IsNil() {
            return nilfunc(w)
        } else {
            return etypeinfo.writer(val.Elem(), w)
        }
    }
    return writer, err
}

// putint writes i to the beginning of b in with 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
        }
    }
    panic("not reached")
}