feat: use CIDs as their byte representation instead of a struct

builder.go

@@ -5,7 +5,7 @@ import (
 )
 
 type Builder interface {
-	Sum(data []byte) (*Cid, error)
+	Sum(data []byte) (Cid, error)
 	GetCodec() uint64
 	WithCodec(uint64) Builder
 }
@@ -33,7 +33,7 @@ func (p Prefix) WithCodec(c uint64) Builder {
 	return p
 }
 
-func (p V0Builder) Sum(data []byte) (*Cid, error) {
+func (p V0Builder) Sum(data []byte) (Cid, error) {
 	hash, err := mh.Sum(data, mh.SHA2_256, -1)
 	if err != nil {
 		return nil, err
@@ -52,7 +52,7 @@ func (p V0Builder) WithCodec(c uint64) Builder {
 	return V1Builder{Codec: c, MhType: mh.SHA2_256}
 }
 
-func (p V1Builder) Sum(data []byte) (*Cid, error) {
+func (p V1Builder) Sum(data []byte) (Cid, error) {
 	mhLen := p.MhLength
 	if mhLen <= 0 {
 		mhLen = -1

cid.go

@@ -132,36 +132,53 @@ var CodecToStr = map[uint64]string{
 // 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.
-func NewCidV0(mhash mh.Multihash) *Cid {
-	return &Cid{
-		version: 0,
-		codec:   DagProtobuf,
-		hash:    mhash,
-	}
+func NewCidV0(mhash mh.Multihash) Cid {
+	return newCid(0, DagProtobuf, mhash)
 }
 
 // NewCidV1 returns a new Cid using the given multicodec-packed
 // content type.
-func NewCidV1(codecType uint64, mhash mh.Multihash) *Cid {
-	return &Cid{
-		version: 1,
-		codec:   codecType,
-		hash:    mhash,
+func NewCidV1(codecType uint64, mhash mh.Multihash) Cid {
+	return newCid(1, codecType, mhash)
+}
+
+func newCid(version, codecType uint64, mhash mh.Multihash) Cid {
+	hashlen := len(mhash)
+	// two 8 bytes (max) numbers plus hash
+	buf := make([]byte, 2*binary.MaxVarintLen64+hashlen)
+	n := binary.PutUvarint(buf, version)
+	n += binary.PutUvarint(buf[n:], codecType)
+	cn := copy(buf[n:], mhash)
+	if cn != hashlen {
+		panic("copy hash length is inconsistent")
 	}
+
+	return Cid(buf[:n+hashlen])
 }
 
 // Cid represents a self-describing content adressed
 // identifier. It is formed by a Version, a Codec (which indicates
 // a multicodec-packed content type) and a Multihash.
-type Cid struct {
-	version uint64
-	codec   uint64
-	hash    mh.Multihash
+// Byte layout: [version, codec, multihash]
+// - version uvarint
+// - codec uvarint
+// - hash mh.Multihash
+type Cid []byte
+
+func (c Cid) version() uint64 {
+	v, _ := binary.Uvarint(c)
+	return v
+}
+
+func (c Cid) codec() uint64 {
+	_, n := binary.Uvarint(c)
+	codec, _ := binary.Uvarint(c[n:])
+	return codec
 }
 
 // Parse is a short-hand function to perform Decode, Cast etc... on
 // a generic interface{} type.
-func Parse(v interface{}) (*Cid, error) {
+func Parse(v interface{}) (Cid, error) {
 	switch v2 := v.(type) {
 	case string:
 		if strings.Contains(v2, "/ipfs/") {
@@ -172,7 +189,7 @@ func Parse(v interface{}) (*Cid, error) {
 		return Cast(v2)
 	case mh.Multihash:
 		return NewCidV0(v2), nil
-	case *Cid:
+	case Cid:
 		return v2, nil
 	default:
 		return nil, fmt.Errorf("can't parse %+v as Cid", v2)
@@ -191,7 +208,7 @@ func Parse(v interface{}) (*Cid, error) {
 // 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) {
+func Decode(v string) (Cid, error) {
 	if len(v) < 2 {
 		return nil, ErrCidTooShort
 	}
@@ -257,18 +274,14 @@ func uvError(read int) error {
 //
 // 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) {
+func Cast(data []byte) (Cid, error) {
 	if len(data) == 34 && data[0] == 18 && data[1] == 32 {
 		h, err := mh.Cast(data)
 		if err != nil {
 			return nil, err
 		}
 
-		return &Cid{
-			codec:   DagProtobuf,
-			version: 0,
-			hash:    h,
-		}, nil
+		return NewCidV0(h), nil
 	}
 
 	vers, n := binary.Uvarint(data)
@@ -280,7 +293,7 @@ func Cast(data []byte) (*Cid, error) {
 		return nil, fmt.Errorf("invalid cid version number: %d", vers)
 	}
 
-	codec, cn := binary.Uvarint(data[n:])
+	_, cn := binary.Uvarint(data[n:])
 	if err := uvError(cn); err != nil {
 		return nil, err
 	}
@@ -291,25 +304,21 @@ func Cast(data []byte) (*Cid, error) {
 		return nil, err
 	}
 
-	return &Cid{
-		version: vers,
-		codec:   codec,
-		hash:    h,
-	}, nil
+	return Cid(data[0 : n+cn+len(h)]), nil
 }
 
 // Type returns the multicodec-packed content type of a Cid.
-func (c *Cid) Type() uint64 {
-	return c.codec
+func (c Cid) Type() uint64 {
+	return c.codec()
 }
 
 // String returns the default string representation of a
 // Cid. Currently, Base58 is used as the encoding for the
 // multibase string.
-func (c *Cid) String() string {
-	switch c.version {
+func (c Cid) String() string {
+	switch c.version() {
 	case 0:
-		return c.hash.B58String()
+		return c.Hash().B58String()
 	case 1:
 		mbstr, err := mbase.Encode(mbase.Base58BTC, c.bytesV1())
 		if err != nil {
@@ -324,13 +333,13 @@ func (c *Cid) String() string {
 
 // String returns the string representation of a Cid
 // encoded is selected base
-func (c *Cid) StringOfBase(base mbase.Encoding) (string, error) {
-	switch c.version {
+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
+		return c.Hash().B58String(), nil
 	case 1:
 		return mbase.Encode(base, c.bytesV1())
 	default:
@@ -341,10 +350,10 @@ func (c *Cid) StringOfBase(base mbase.Encoding) (string, error) {
 // 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 {
+func (c Cid) Encode(base mbase.Encoder) string {
+	switch c.version() {
 	case 0:
-		return c.hash.B58String()
+		return c.Hash().B58String()
 	case 1:
 		return base.Encode(c.bytesV1())
 	default:
@@ -353,15 +362,20 @@ func (c *Cid) Encode(base mbase.Encoder) string {
 }
 
 // Hash returns the multihash contained by a Cid.
-func (c *Cid) Hash() mh.Multihash {
-	return c.hash
+func (c Cid) Hash() mh.Multihash {
+	// skip version length
+	_, n1 := binary.Uvarint(c)
+	// skip codec length
+	_, n2 := binary.Uvarint(c[n1:])
+
+	return mh.Multihash(c[n1+n2:])
 }
 
 // Bytes returns the byte representation of a Cid.
 // The output of bytes can be parsed back into a Cid
 // with Cast().
-func (c *Cid) Bytes() []byte {
-	switch c.version {
+func (c Cid) Bytes() []byte {
+	switch c.version() {
 	case 0:
 		return c.bytesV0()
 	case 1:
@@ -371,30 +385,19 @@ func (c *Cid) Bytes() []byte {
 	}
 }
 
-func (c *Cid) bytesV0() []byte {
-	return []byte(c.hash)
+func (c Cid) bytesV0() []byte {
+	return []byte(c.Hash())
 }
 
-func (c *Cid) bytesV1() []byte {
-	// two 8 bytes (max) numbers plus hash
-	buf := make([]byte, 2*binary.MaxVarintLen64+len(c.hash))
-	n := binary.PutUvarint(buf, c.version)
-	n += binary.PutUvarint(buf[n:], c.codec)
-	cn := copy(buf[n:], c.hash)
-	if cn != len(c.hash) {
-		panic("copy hash length is inconsistent")
-	}
-
-	return buf[:n+len(c.hash)]
+func (c Cid) bytesV1() []byte {
+	return []byte(c)
 }
 
 // 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.codec == o.codec &&
-		c.version == o.version &&
-		bytes.Equal(c.hash, o.hash)
+func (c Cid) Equals(o Cid) bool {
+	return bytes.Equal(c, o)
 }
 
 // UnmarshalJSON parses the JSON representation of a Cid.
@@ -419,9 +422,8 @@ func (c *Cid) UnmarshalJSON(b []byte) error {
 		return err
 	}
 
-	c.version = out.version
-	c.hash = out.hash
-	c.codec = out.codec
+	*c = out[:]
+
 	return nil
 }
 
@@ -436,26 +438,26 @@ func (c Cid) MarshalJSON() ([]byte, error) {
 }
 
 // KeyString casts the result of cid.Bytes() as a string, and returns it.
-func (c *Cid) KeyString() string {
+func (c Cid) KeyString() string {
 	return string(c.Bytes())
 }
 
 // Loggable returns a Loggable (as defined by
 // https://godoc.org/github.com/ipfs/go-log).
-func (c *Cid) Loggable() map[string]interface{} {
+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 {
-	dec, _ := mh.Decode(c.hash) // assuming we got a valid multiaddr, this will not error
+func (c Cid) Prefix() Prefix {
+	dec, _ := mh.Decode(c.Hash()) // assuming we got a valid multiaddr, this will not error
 	return Prefix{
 		MhType:   dec.Code,
 		MhLength: dec.Length,
-		Version:  c.version,
-		Codec:    c.codec,
+		Version:  c.version(),
+		Codec:    c.codec(),
 	}
 }
 
@@ -474,7 +476,7 @@ type Prefix struct {
 
 // 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) {
+func (p Prefix) Sum(data []byte) (Cid, error) {
 	hash, err := mh.Sum(data, p.MhType, p.MhLength)
 	if err != nil {
 		return nil, err

cid_fuzz.go

@@ -23,7 +23,7 @@ func Fuzz(data []byte) int {
 	if err != nil {
 		panic(err.Error())
 	}
-	cid2 := &Cid{}
+	cid2 := Cid{}
 	err = cid2.UnmarshalJSON(json)
 	if err != nil {
 		panic(err.Error())

cid_test.go

@@ -37,16 +37,16 @@ var tCodecs = map[uint64]string{
 	DecredTx:           "decred-tx",
 }
 
-func assertEqual(t *testing.T, a, b *Cid) {
-	if a.codec != b.codec {
+func assertEqual(t *testing.T, a, b Cid) {
+	if a.codec() != b.codec() {
 		t.Fatal("mismatch on type")
 	}
 
-	if a.version != b.version {
+	if a.version() != b.version() {
 		t.Fatal("mismatch on version")
 	}
 
-	if !bytes.Equal(a.hash, b.hash) {
+	if !bytes.Equal(a.Hash(), b.Hash()) {
 		t.Fatal("multihash mismatch")
 	}
 }
@@ -77,11 +77,7 @@ func TestBasicMarshaling(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	cid := &Cid{
-		codec:   7,
-		version: 1,
-		hash:    h,
-	}
+	cid := newCid(1, 7, h)
 
 	data := cid.Bytes()
 
@@ -107,11 +103,7 @@ func TestBasesMarshaling(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	cid := &Cid{
-		codec:   7,
-		version: 1,
-		hash:    h,
-	}
+	cid := newCid(1, 7, h)
 
 	data := cid.Bytes()
 
@@ -179,12 +171,12 @@ func TestV0Handling(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	if cid.version != 0 {
+	if cid.version() != 0 {
 		t.Fatal("should have gotten version 0 cid")
 	}
 
-	if cid.hash.B58String() != old {
-		t.Fatal("marshaling roundtrip failed")
+	if cid.Hash().B58String() != old {
+		t.Fatalf("marshaling roundtrip failed: %s != %s", cid.Hash().B58String(), old)
 	}
 
 	if cid.String() != old {
@@ -306,9 +298,7 @@ func TestPrefixRoundtrip(t *testing.T) {
 func Test16BytesVarint(t *testing.T) {
 	data := []byte("this is some test content")
 	hash, _ := mh.Sum(data, mh.SHA2_256, -1)
-	c := NewCidV1(DagCBOR, hash)
-
-	c.codec = 1 << 63
+	c := newCid(1, 1<<63, hash)
 	_ = c.Bytes()
 }
 
@@ -351,8 +341,8 @@ func TestParse(t *testing.T) {
 		if err != nil {
 			return err
 		}
-		if cid.version != 0 {
-			return fmt.Errorf("expected version 0, got %s", string(cid.version))
+		if cid.version() != 0 {
+			return fmt.Errorf("expected version 0, got %s", string(cid.version()))
 		}
 		actual := cid.Hash().B58String()
 		if actual != expected {
@@ -424,18 +414,18 @@ func TestJsonRoundTrip(t *testing.T) {
 	}
 	var actual Cid
 	err = json.Unmarshal(enc, &actual)
-	if !exp.Equals(&actual) {
+	if !exp.Equals(actual) {
 		t.Fatal("cids not equal for *Cid")
 	}
 
 	// Verify it works for a Cid.
-	enc, err = json.Marshal(*exp)
+	enc, err = json.Marshal(exp)
 	if err != nil {
 		t.Fatal(err)
 	}
 	var actual2 Cid
 	err = json.Unmarshal(enc, &actual2)
-	if !exp.Equals(&actual2) {
+	if !exp.Equals(actual2) {
 		t.Fatal("cids not equal for Cid")
 	}
 }
@@ -444,7 +434,10 @@ func BenchmarkStringV1(b *testing.B) {
 	data := []byte("this is some test content")
 	hash, _ := mh.Sum(data, mh.SHA2_256, -1)
 	cid := NewCidV1(Raw, hash)
+
+	b.ReportAllocs()
 	b.ResetTimer()
+
 	count := 0
 	for i := 0; i < b.N; i++ {
 		count += len(cid.String())
@@ -453,3 +446,22 @@ func BenchmarkStringV1(b *testing.B) {
 		b.FailNow()
 	}
 }
+
+// making sure we don't allocate when returning bytes
+func BenchmarkBytesV1(b *testing.B) {
+	data := []byte("this is some test content")
+	hash, _ := mh.Sum(data, mh.SHA2_256, -1)
+	cid := NewCidV1(Raw, hash)
+
+	b.ReportAllocs()
+	b.ResetTimer()
+
+	count := 0
+	for i := 0; i < b.N; i++ {
+		count += len(cid.Bytes())
+		count += len([]byte(cid))
+	}
+	if count != 36*2*b.N {
+		b.FailNow()
+	}
+}

set.go

@@ -12,18 +12,18 @@ func NewSet() *Set {
 }
 
 // Add puts a Cid in the Set.
-func (s *Set) Add(c *Cid) {
+func (s *Set) Add(c Cid) {
 	s.set[string(c.Bytes())] = struct{}{}
 }
 
 // Has returns if the Set contains a given Cid.
-func (s *Set) Has(c *Cid) bool {
+func (s *Set) Has(c Cid) bool {
 	_, ok := s.set[string(c.Bytes())]
 	return ok
 }
 
 // Remove deletes a Cid from the Set.
-func (s *Set) Remove(c *Cid) {
+func (s *Set) Remove(c Cid) {
 	delete(s.set, string(c.Bytes()))
 }
 
@@ -33,8 +33,8 @@ func (s *Set) Len() int {
 }
 
 // Keys returns the Cids in the set.
-func (s *Set) Keys() []*Cid {
-	out := make([]*Cid, 0, len(s.set))
+func (s *Set) Keys() []Cid {
+	out := make([]Cid, 0, len(s.set))
 	for k := range s.set {
 		c, _ := Cast([]byte(k))
 		out = append(out, c)
@@ -44,7 +44,7 @@ func (s *Set) Keys() []*Cid {
 
 // Visit adds a Cid to the set only if it is
 // not in it already.
-func (s *Set) Visit(c *Cid) bool {
+func (s *Set) Visit(c Cid) bool {
 	if !s.Has(c) {
 		s.Add(c)
 		return true
@@ -55,7 +55,7 @@ func (s *Set) Visit(c *Cid) bool {
 
 // ForEach allows to run a custom function on each
 // Cid in the set.
-func (s *Set) ForEach(f func(c *Cid) error) error {
+func (s *Set) ForEach(f func(c Cid) error) error {
 	for cs := range s.set {
 		c, _ := Cast([]byte(cs))
 		err := f(c)

set_test.go

@@ -8,7 +8,7 @@ import (
 	mh "github.com/multiformats/go-multihash"
 )
 
-func makeRandomCid(t *testing.T) *Cid {
+func makeRandomCid(t *testing.T) Cid {
 	p := make([]byte, 256)
 	_, err := rand.Read(p)
 	if err != nil {
@@ -20,11 +20,7 @@ func makeRandomCid(t *testing.T) *Cid {
 		t.Fatal(err)
 	}
 
-	cid := &Cid{
-		codec:   7,
-		version: 1,
-		hash:    h,
-	}
+	cid := NewCidV1(7, h)
 
 	return cid
 }
@@ -54,8 +50,8 @@ func TestSet(t *testing.T) {
 		t.Error("visit should return false")
 	}
 
-	foreach := []*Cid{}
-	foreachF := func(c *Cid) error {
+	foreach := []Cid{}
+	foreachF := func(c Cid) error {
 		foreach = append(foreach, c)
 		return nil
 	}
@@ -68,7 +64,7 @@ func TestSet(t *testing.T) {
 		t.Error("ForEach should have visited 1 element")
 	}
 
-	foreachErr := func(c *Cid) error {
+	foreachErr := func(c Cid) error {
 		return errors.New("test")
 	}