-
Notifications
You must be signed in to change notification settings - Fork 47
/
cid.go
817 lines (708 loc) · 21.3 KB
/
cid.go
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
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
// Package cid implements the Content-IDentifiers specification
// (https://github.com/ipld/cid) in Go. CIDs are
// self-describing content-addressed identifiers useful for
// distributed information systems. CIDs are used in the IPFS
// (https://ipfs.io) project ecosystem.
//
// CIDs have two major versions. A CIDv0 corresponds to a multihash of type
// DagProtobuf, is deprecated and exists for compatibility reasons. Usually,
// CIDv1 should be used.
//
// A CIDv1 has four parts:
//
// <cidv1> ::= <multibase-prefix><cid-version><multicodec-packed-content-type><multihash-content-address>
//
// As shown above, the CID implementation relies heavily on Multiformats,
// particularly Multibase
// (https://github.com/multiformats/go-multibase), Multicodec
// (https://github.com/multiformats/multicodec) and Multihash
// implementations (https://github.com/multiformats/go-multihash).
package cid
import (
"bytes"
"encoding"
"encoding/binary"
"encoding/json"
"errors"
"fmt"
"io"
"strings"
mbase "github.com/multiformats/go-multibase"
mh "github.com/multiformats/go-multihash"
varint "github.com/multiformats/go-varint"
)
// UnsupportedVersionString just holds an error message
const UnsupportedVersionString = "<unsupported cid version>"
// ErrInvalidCid is an error that indicates that a CID is invalid.
type ErrInvalidCid struct {
Err error
}
func (e ErrInvalidCid) Error() string {
return fmt.Sprintf("invalid cid: %s", e.Err)
}
func (e ErrInvalidCid) Unwrap() error {
return e.Err
}
func (e ErrInvalidCid) Is(err error) bool {
switch err.(type) {
case ErrInvalidCid, *ErrInvalidCid:
return true
default:
return false
}
}
var (
// ErrCidTooShort means that the cid passed to decode was not long
// enough to be a valid Cid
ErrCidTooShort = ErrInvalidCid{errors.New("cid too short")}
// ErrInvalidEncoding means that selected encoding is not supported
// by this Cid version
ErrInvalidEncoding = errors.New("invalid base encoding")
)
// Consts below are DEPRECATED and left only for legacy reasons:
// <https://github.com/ipfs/go-cid/pull/137>
// Modern code should use consts from go-multicodec instead:
// <https://github.com/multiformats/go-multicodec>
const (
// common ones
Raw = 0x55
DagProtobuf = 0x70 // https://ipld.io/docs/codecs/known/dag-pb/
DagCBOR = 0x71 // https://ipld.io/docs/codecs/known/dag-cbor/
DagJSON = 0x0129 // https://ipld.io/docs/codecs/known/dag-json/
Libp2pKey = 0x72 // https://github.com/libp2p/specs/blob/master/peer-ids/peer-ids.md#peer-ids
// other
GitRaw = 0x78
DagJOSE = 0x85 // https://ipld.io/specs/codecs/dag-jose/spec/
EthBlock = 0x90
EthBlockList = 0x91
EthTxTrie = 0x92
EthTx = 0x93
EthTxReceiptTrie = 0x94
EthTxReceipt = 0x95
EthStateTrie = 0x96
EthAccountSnapshot = 0x97
EthStorageTrie = 0x98
BitcoinBlock = 0xb0
BitcoinTx = 0xb1
ZcashBlock = 0xc0
ZcashTx = 0xc1
DecredBlock = 0xe0
DecredTx = 0xe1
DashBlock = 0xf0
DashTx = 0xf1
FilCommitmentUnsealed = 0xf101
FilCommitmentSealed = 0xf102
)
// tryNewCidV0 tries to convert a multihash into a CIDv0 CID and returns an
// error on failure.
func tryNewCidV0(mhash mh.Multihash) (Cid, error) {
// Need to make sure hash is valid for CidV0 otherwise we will
// incorrectly detect it as CidV1 in the Version() method
dec, err := mh.Decode(mhash)
if err != nil {
return Undef, ErrInvalidCid{err}
}
if dec.Code != mh.SHA2_256 || dec.Length != 32 {
return Undef, ErrInvalidCid{fmt.Errorf("invalid hash for cidv0 %d-%d", dec.Code, dec.Length)}
}
return Cid{string(mhash)}, nil
}
// NewCidV0 returns a Cid-wrapped multihash.
// They exist to allow IPFS to work with Cids while keeping
// compatibility with the plain-multihash format used used in IPFS.
// NewCidV1 should be used preferentially.
//
// Panics if the multihash isn't sha2-256.
func NewCidV0(mhash mh.Multihash) Cid {
c, err := tryNewCidV0(mhash)
if err != nil {
panic(err)
}
return c
}
// NewCidV1 returns a new Cid using the given multicodec-packed
// content type.
//
// Panics if the multihash is invalid.
func NewCidV1(codecType uint64, mhash mh.Multihash) Cid {
hashlen := len(mhash)
// Two 8 bytes (max) numbers plus hash.
// We use strings.Builder to only allocate once.
var b strings.Builder
b.Grow(1 + varint.UvarintSize(codecType) + hashlen)
b.WriteByte(1)
var buf [binary.MaxVarintLen64]byte
n := varint.PutUvarint(buf[:], codecType)
b.Write(buf[:n])
cn, _ := b.Write(mhash)
if cn != hashlen {
panic("copy hash length is inconsistent")
}
return Cid{b.String()}
}
var (
_ encoding.BinaryMarshaler = Cid{}
_ encoding.BinaryUnmarshaler = (*Cid)(nil)
_ encoding.TextMarshaler = Cid{}
_ encoding.TextUnmarshaler = (*Cid)(nil)
)
// Cid represents a self-describing content addressed
// identifier. It is formed by a Version, a Codec (which indicates
// a multicodec-packed content type) and a Multihash.
type Cid struct{ str string }
// Undef can be used to represent a nil or undefined Cid, using Cid{}
// directly is also acceptable.
var Undef = Cid{}
// Defined returns true if a Cid is defined
// Calling any other methods on an undefined Cid will result in
// undefined behavior.
func (c Cid) Defined() bool {
return c.str != ""
}
// Parse is a short-hand function to perform Decode, Cast etc... on
// a generic interface{} type.
func Parse(v interface{}) (Cid, error) {
switch v2 := v.(type) {
case string:
if strings.Contains(v2, "/ipfs/") {
return Decode(strings.Split(v2, "/ipfs/")[1])
}
return Decode(v2)
case []byte:
return Cast(v2)
case mh.Multihash:
return tryNewCidV0(v2)
case Cid:
return v2, nil
default:
return Undef, ErrInvalidCid{fmt.Errorf("can't parse %+v as Cid", v2)}
}
}
// MustParse calls Parse but will panic on error.
func MustParse(v interface{}) Cid {
c, err := Parse(v)
if err != nil {
panic(err)
}
return c
}
// Decode parses a Cid-encoded string and returns a Cid object.
// For CidV1, a Cid-encoded string is primarily a multibase string:
//
// <multibase-type-code><base-encoded-string>
//
// The base-encoded string represents a:
//
// <version><codec-type><multihash>
//
// Decode will also detect and parse CidV0 strings. Strings
// starting with "Qm" are considered CidV0 and treated directly
// as B58-encoded multihashes.
func Decode(v string) (Cid, error) {
if len(v) < 2 {
return Undef, ErrCidTooShort
}
if len(v) == 46 && v[:2] == "Qm" {
hash, err := mh.FromB58String(v)
if err != nil {
return Undef, ErrInvalidCid{err}
}
return tryNewCidV0(hash)
}
_, data, err := mbase.Decode(v)
if err != nil {
return Undef, ErrInvalidCid{err}
}
return Cast(data)
}
// Extract the encoding from a Cid. If Decode on the same string did
// not return an error neither will this function.
func ExtractEncoding(v string) (mbase.Encoding, error) {
if len(v) < 2 {
return -1, ErrCidTooShort
}
if len(v) == 46 && v[:2] == "Qm" {
return mbase.Base58BTC, nil
}
encoding := mbase.Encoding(v[0])
// check encoding is valid
_, err := mbase.NewEncoder(encoding)
if err != nil {
return -1, ErrInvalidCid{err}
}
return encoding, nil
}
// Cast takes a Cid data slice, parses it and returns a Cid.
// For CidV1, the data buffer is in the form:
//
// <version><codec-type><multihash>
//
// CidV0 are also supported. In particular, data buffers starting
// with length 34 bytes, which starts with bytes [18,32...] are considered
// binary multihashes.
//
// Please use decode when parsing a regular Cid string, as Cast does not
// expect multibase-encoded data. Cast accepts the output of Cid.Bytes().
func Cast(data []byte) (Cid, error) {
nr, c, err := CidFromBytes(data)
if err != nil {
return Undef, ErrInvalidCid{err}
}
if nr != len(data) {
return Undef, ErrInvalidCid{fmt.Errorf("trailing bytes in data buffer passed to cid Cast")}
}
return c, nil
}
// UnmarshalBinary is equivalent to Cast(). It implements the
// encoding.BinaryUnmarshaler interface.
func (c *Cid) UnmarshalBinary(data []byte) error {
casted, err := Cast(data)
if err != nil {
return err
}
c.str = casted.str
return nil
}
// UnmarshalText is equivalent to Decode(). It implements the
// encoding.TextUnmarshaler interface.
func (c *Cid) UnmarshalText(text []byte) error {
decodedCid, err := Decode(string(text))
if err != nil {
return err
}
c.str = decodedCid.str
return nil
}
// Version returns the Cid version.
func (c Cid) Version() uint64 {
if len(c.str) == 34 && c.str[0] == 18 && c.str[1] == 32 {
return 0
}
return 1
}
// Type returns the multicodec-packed content type of a Cid.
func (c Cid) Type() uint64 {
if c.Version() == 0 {
return DagProtobuf
}
_, n, _ := uvarint(c.str)
codec, _, _ := uvarint(c.str[n:])
return codec
}
// String returns the default string representation of a
// Cid. Currently, Base32 is used for CIDV1 as the encoding for the
// multibase string, Base58 is used for CIDV0.
func (c Cid) String() string {
switch c.Version() {
case 0:
return c.Hash().B58String()
case 1:
mbstr, err := mbase.Encode(mbase.Base32, c.Bytes())
if err != nil {
panic("should not error with hardcoded mbase: " + err.Error())
}
return mbstr
default:
panic("not possible to reach this point")
}
}
// String returns the string representation of a Cid
// encoded is selected base
func (c Cid) StringOfBase(base mbase.Encoding) (string, error) {
switch c.Version() {
case 0:
if base != mbase.Base58BTC {
return "", ErrInvalidEncoding
}
return c.Hash().B58String(), nil
case 1:
return mbase.Encode(base, c.Bytes())
default:
panic("not possible to reach this point")
}
}
// Encode return the string representation of a Cid in a given base
// when applicable. Version 0 Cid's are always in Base58 as they do
// not take a multibase prefix.
func (c Cid) Encode(base mbase.Encoder) string {
switch c.Version() {
case 0:
return c.Hash().B58String()
case 1:
return base.Encode(c.Bytes())
default:
panic("not possible to reach this point")
}
}
// Hash returns the multihash contained by a Cid.
func (c Cid) Hash() mh.Multihash {
bytes := c.Bytes()
if c.Version() == 0 {
return mh.Multihash(bytes)
}
// skip version length
_, n1, _ := varint.FromUvarint(bytes)
// skip codec length
_, n2, _ := varint.FromUvarint(bytes[n1:])
return mh.Multihash(bytes[n1+n2:])
}
// Bytes returns the byte representation of a Cid.
// The output of bytes can be parsed back into a Cid
// with Cast().
//
// If c.Defined() == false, it return a nil slice and may not
// be parsable with Cast().
func (c Cid) Bytes() []byte {
if !c.Defined() {
return nil
}
return []byte(c.str)
}
// ByteLen returns the length of the CID in bytes.
// It's equivalent to `len(c.Bytes())`, but works without an allocation,
// and should therefore be preferred.
//
// (See also the WriteTo method for other important operations that work without allocation.)
func (c Cid) ByteLen() int {
return len(c.str)
}
// WriteBytes writes the CID bytes to the given writer.
// This method works without incurring any allocation.
//
// (See also the ByteLen method for other important operations that work without allocation.)
func (c Cid) WriteBytes(w io.Writer) (int, error) {
n, err := io.WriteString(w, c.str)
if err != nil {
return n, err
}
if n != len(c.str) {
return n, fmt.Errorf("failed to write entire cid string")
}
return n, nil
}
// MarshalBinary is equivalent to Bytes(). It implements the
// encoding.BinaryMarshaler interface.
func (c Cid) MarshalBinary() ([]byte, error) {
return c.Bytes(), nil
}
// MarshalText is equivalent to String(). It implements the
// encoding.TextMarshaler interface.
func (c Cid) MarshalText() ([]byte, error) {
return []byte(c.String()), nil
}
// Equals checks that two Cids are the same.
// In order for two Cids to be considered equal, the
// Version, the Codec and the Multihash must match.
func (c Cid) Equals(o Cid) bool {
return c == o
}
// UnmarshalJSON parses the JSON representation of a Cid.
func (c *Cid) UnmarshalJSON(b []byte) error {
if len(b) < 2 {
return ErrInvalidCid{fmt.Errorf("invalid cid json blob")}
}
obj := struct {
CidTarget string `json:"/"`
}{}
objptr := &obj
err := json.Unmarshal(b, &objptr)
if err != nil {
return ErrInvalidCid{err}
}
if objptr == nil {
*c = Cid{}
return nil
}
if obj.CidTarget == "" {
return ErrInvalidCid{fmt.Errorf("cid was incorrectly formatted")}
}
out, err := Decode(obj.CidTarget)
if err != nil {
return ErrInvalidCid{err}
}
*c = out
return nil
}
// MarshalJSON procudes a JSON representation of a Cid, which looks as follows:
//
// { "/": "<cid-string>" }
//
// Note that this formatting comes from the IPLD specification
// (https://github.com/ipld/specs/tree/master/ipld)
func (c Cid) MarshalJSON() ([]byte, error) {
if !c.Defined() {
return []byte("null"), nil
}
return []byte(fmt.Sprintf("{\"/\":\"%s\"}", c.String())), nil
}
// KeyString returns the binary representation of the Cid as a string
func (c Cid) KeyString() string {
return c.str
}
// Loggable returns a Loggable (as defined by
// https://godoc.org/github.com/ipfs/go-log).
func (c Cid) Loggable() map[string]interface{} {
return map[string]interface{}{
"cid": c,
}
}
// Prefix builds and returns a Prefix out of a Cid.
func (c Cid) Prefix() Prefix {
if c.Version() == 0 {
return Prefix{
MhType: mh.SHA2_256,
MhLength: 32,
Version: 0,
Codec: DagProtobuf,
}
}
offset := 0
version, n, _ := uvarint(c.str[offset:])
offset += n
codec, n, _ := uvarint(c.str[offset:])
offset += n
mhtype, n, _ := uvarint(c.str[offset:])
offset += n
mhlen, _, _ := uvarint(c.str[offset:])
return Prefix{
MhType: mhtype,
MhLength: int(mhlen),
Version: version,
Codec: codec,
}
}
// Prefix represents all the metadata of a Cid,
// that is, the Version, the Codec, the Multihash type
// and the Multihash length. It does not contains
// any actual content information.
// NOTE: The use -1 in MhLength to mean default length is deprecated,
//
// use the V0Builder or V1Builder structures instead
type Prefix struct {
Version uint64
Codec uint64
MhType uint64
MhLength int
}
// Sum uses the information in a prefix to perform a multihash.Sum()
// and return a newly constructed Cid with the resulting multihash.
func (p Prefix) Sum(data []byte) (Cid, error) {
length := p.MhLength
if p.MhType == mh.IDENTITY {
length = -1
}
if p.Version == 0 && (p.MhType != mh.SHA2_256 ||
(p.MhLength != 32 && p.MhLength != -1)) {
return Undef, ErrInvalidCid{fmt.Errorf("invalid v0 prefix")}
}
hash, err := mh.Sum(data, p.MhType, length)
if err != nil {
return Undef, ErrInvalidCid{err}
}
switch p.Version {
case 0:
return NewCidV0(hash), nil
case 1:
return NewCidV1(p.Codec, hash), nil
default:
return Undef, ErrInvalidCid{fmt.Errorf("invalid cid version")}
}
}
// Bytes returns a byte representation of a Prefix. It looks like:
//
// <version><codec><mh-type><mh-length>
func (p Prefix) Bytes() []byte {
size := varint.UvarintSize(p.Version)
size += varint.UvarintSize(p.Codec)
size += varint.UvarintSize(p.MhType)
size += varint.UvarintSize(uint64(p.MhLength))
buf := make([]byte, size)
n := varint.PutUvarint(buf, p.Version)
n += varint.PutUvarint(buf[n:], p.Codec)
n += varint.PutUvarint(buf[n:], p.MhType)
n += varint.PutUvarint(buf[n:], uint64(p.MhLength))
if n != size {
panic("size mismatch")
}
return buf
}
// PrefixFromBytes parses a Prefix-byte representation onto a
// Prefix.
func PrefixFromBytes(buf []byte) (Prefix, error) {
r := bytes.NewReader(buf)
vers, err := varint.ReadUvarint(r)
if err != nil {
return Prefix{}, ErrInvalidCid{err}
}
codec, err := varint.ReadUvarint(r)
if err != nil {
return Prefix{}, ErrInvalidCid{err}
}
mhtype, err := varint.ReadUvarint(r)
if err != nil {
return Prefix{}, ErrInvalidCid{err}
}
mhlen, err := varint.ReadUvarint(r)
if err != nil {
return Prefix{}, ErrInvalidCid{err}
}
return Prefix{
Version: vers,
Codec: codec,
MhType: mhtype,
MhLength: int(mhlen),
}, nil
}
func CidFromBytes(data []byte) (int, Cid, error) {
if len(data) > 2 && data[0] == mh.SHA2_256 && data[1] == 32 {
if len(data) < 34 {
return 0, Undef, ErrInvalidCid{fmt.Errorf("not enough bytes for cid v0")}
}
h, err := mh.Cast(data[:34])
if err != nil {
return 0, Undef, ErrInvalidCid{err}
}
return 34, Cid{string(h)}, nil
}
vers, n, err := varint.FromUvarint(data)
if err != nil {
return 0, Undef, ErrInvalidCid{err}
}
if vers != 1 {
return 0, Undef, ErrInvalidCid{fmt.Errorf("expected 1 as the cid version number, got: %d", vers)}
}
_, cn, err := varint.FromUvarint(data[n:])
if err != nil {
return 0, Undef, ErrInvalidCid{err}
}
mhnr, _, err := mh.MHFromBytes(data[n+cn:])
if err != nil {
return 0, Undef, ErrInvalidCid{err}
}
l := n + cn + mhnr
return l, Cid{string(data[0:l])}, nil
}
func toBufByteReader(r io.Reader, dst []byte) *bufByteReader {
// If the reader already implements ByteReader, use it directly.
// Otherwise, use a fallback that does 1-byte Reads.
if br, ok := r.(io.ByteReader); ok {
return &bufByteReader{direct: br, dst: dst}
}
return &bufByteReader{fallback: r, dst: dst}
}
type bufByteReader struct {
direct io.ByteReader
fallback io.Reader
dst []byte
}
func (r *bufByteReader) ReadByte() (byte, error) {
// The underlying reader has ReadByte; use it.
if br := r.direct; br != nil {
b, err := br.ReadByte()
if err != nil {
return 0, err
}
r.dst = append(r.dst, b)
return b, nil
}
// Fall back to a one-byte Read.
// TODO: consider reading straight into dst,
// once we have benchmarks and if they prove that to be faster.
var p [1]byte
if _, err := io.ReadFull(r.fallback, p[:]); err != nil {
return 0, err
}
r.dst = append(r.dst, p[0])
return p[0], nil
}
// CidFromReader reads a precise number of bytes for a CID from a given reader.
// It returns the number of bytes read, the CID, and any error encountered.
// The number of bytes read is accurate even if a non-nil error is returned.
//
// It's recommended to supply a reader that buffers and implements io.ByteReader,
// as CidFromReader has to do many single-byte reads to decode varints.
// If the argument only implements io.Reader, single-byte Read calls are used instead.
//
// If the Reader is found to yield zero bytes, an io.EOF error is returned directly, in all
// other error cases, an ErrInvalidCid, wrapping the original error, is returned.
func CidFromReader(r io.Reader) (int, Cid, error) {
// 64 bytes is enough for any CIDv0,
// and it's enough for most CIDv1s in practice.
// If the digest is too long, we'll allocate more.
br := toBufByteReader(r, make([]byte, 0, 64))
// We read the first varint, to tell if this is a CIDv0 or a CIDv1.
// The varint package wants a io.ByteReader, so we must wrap our io.Reader.
vers, err := varint.ReadUvarint(br)
if err != nil {
if err == io.EOF {
// First-byte read in ReadUvarint errors with io.EOF, so reader has no data.
// Subsequent reads with an EOF will return io.ErrUnexpectedEOF and be wrapped here.
return 0, Undef, err
}
return len(br.dst), Undef, ErrInvalidCid{err}
}
// If we have a CIDv0, read the rest of the bytes and cast the buffer.
if vers == mh.SHA2_256 {
if n, err := io.ReadFull(r, br.dst[1:34]); err != nil {
return len(br.dst) + n, Undef, ErrInvalidCid{err}
}
br.dst = br.dst[:34]
h, err := mh.Cast(br.dst)
if err != nil {
return len(br.dst), Undef, ErrInvalidCid{err}
}
return len(br.dst), Cid{string(h)}, nil
}
if vers != 1 {
return len(br.dst), Undef, ErrInvalidCid{fmt.Errorf("expected 1 as the cid version number, got: %d", vers)}
}
// CID block encoding multicodec.
_, err = varint.ReadUvarint(br)
if err != nil {
return len(br.dst), Undef, ErrInvalidCid{err}
}
// We could replace most of the code below with go-multihash's ReadMultihash.
// Note that it would save code, but prevent reusing buffers.
// Plus, we already have a ByteReader now.
mhStart := len(br.dst)
// Multihash hash function code.
_, err = varint.ReadUvarint(br)
if err != nil {
return len(br.dst), Undef, ErrInvalidCid{err}
}
// Multihash digest length.
mhl, err := varint.ReadUvarint(br)
if err != nil {
return len(br.dst), Undef, ErrInvalidCid{err}
}
// Refuse to make large allocations to prevent OOMs due to bugs.
const maxDigestAlloc = 32 << 20 // 32MiB
if mhl > maxDigestAlloc {
return len(br.dst), Undef, ErrInvalidCid{fmt.Errorf("refusing to allocate %d bytes for a digest", mhl)}
}
// Fine to convert mhl to int, given maxDigestAlloc.
prefixLength := len(br.dst)
cidLength := prefixLength + int(mhl)
if cidLength > cap(br.dst) {
// If the multihash digest doesn't fit in our initial 64 bytes,
// efficiently extend the slice via append+make.
br.dst = append(br.dst, make([]byte, cidLength-len(br.dst))...)
} else {
// The multihash digest fits inside our buffer,
// so just extend its capacity.
br.dst = br.dst[:cidLength]
}
if n, err := io.ReadFull(r, br.dst[prefixLength:cidLength]); err != nil {
// We can't use len(br.dst) here,
// as we've only read n bytes past prefixLength.
return prefixLength + n, Undef, ErrInvalidCid{err}
}
// This simply ensures the multihash is valid.
// TODO: consider removing this bit, as it's probably redundant;
// for now, it helps ensure consistency with CidFromBytes.
_, _, err = mh.MHFromBytes(br.dst[mhStart:])
if err != nil {
return len(br.dst), Undef, ErrInvalidCid{err}
}
return len(br.dst), Cid{string(br.dst)}, nil
}