diff --git a/.gx/lastpubver b/.gx/lastpubver index 3d7db28..1401252 100644 --- a/.gx/lastpubver +++ b/.gx/lastpubver @@ -1 +1 @@ -0.8.0: QmZFbDTY9jfSBms2MchvYM9oYRbAF19K7Pby47yDBfpPrb +0.9.0: QmPSQnBKM9g7BaUcZCvswUJVscQ1ipjmwxN5PXCjkp9EQ7 diff --git a/builder.go b/builder.go index af33aac..a168832 100644 --- a/builder.go +++ b/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 } @@ -33,10 +33,10 @@ 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 + return Undef, err } return NewCidV0(hash), nil } @@ -52,14 +52,14 @@ 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 } hash, err := mh.Sum(data, p.MhType, mhLen) if err != nil { - return nil, err + return Undef, err } return NewCidV1(p.Codec, hash), nil } diff --git a/cid.go b/cid.go index 6bf2aa5..cfcbcde 100644 --- a/cid.go +++ b/cid.go @@ -132,36 +132,54 @@ 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 { + // 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 { + panic(err) + } + if dec.Code != mh.SHA2_256 || dec.Length != 32 { + panic("invalid hash for cidv0") } + return Cid{string(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 { + hashlen := len(mhash) + // two 8 bytes (max) numbers plus hash + buf := make([]byte, 2*binary.MaxVarintLen64+hashlen) + n := binary.PutUvarint(buf, 1) + n += binary.PutUvarint(buf[n:], codecType) + cn := copy(buf[n:], mhash) + if cn != hashlen { + panic("copy hash length is inconsistent") } + + return Cid{string(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 +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) { +func Parse(v interface{}) (Cid, error) { switch v2 := v.(type) { case string: if strings.Contains(v2, "/ipfs/") { @@ -172,10 +190,10 @@ 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) + return Undef, fmt.Errorf("can't parse %+v as Cid", v2) } } @@ -191,15 +209,15 @@ 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 + return Undef, ErrCidTooShort } if len(v) == 46 && v[:2] == "Qm" { hash, err := mh.FromB58String(v) if err != nil { - return nil, err + return Undef, err } return NewCidV0(hash), nil @@ -207,7 +225,7 @@ func Decode(v string) (*Cid, error) { _, data, err := mbase.Decode(v) if err != nil { - return nil, err + return Undef, err } return Cast(data) @@ -257,61 +275,66 @@ 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 Undef, err } - return &Cid{ - codec: DagProtobuf, - version: 0, - hash: h, - }, nil + return NewCidV0(h), nil } vers, n := binary.Uvarint(data) if err := uvError(n); err != nil { - return nil, err + return Undef, err } - if vers != 0 && vers != 1 { - return nil, fmt.Errorf("invalid cid version number: %d", vers) + if vers != 1 { + return Undef, fmt.Errorf("expected 1 as the cid version number, got: %d", vers) } - codec, cn := binary.Uvarint(data[n:]) + _, cn := binary.Uvarint(data[n:]) if err := uvError(cn); err != nil { - return nil, err + return Undef, err } rest := data[n+cn:] h, err := mh.Cast(rest) if err != nil { - return nil, err + return Undef, err } - return &Cid{ - version: vers, - codec: codec, - hash: h, - }, nil + return Cid{string(data[0 : n+cn+len(h)])}, 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 { - return c.codec +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, 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()) + mbstr, err := mbase.Encode(mbase.Base58BTC, c.Bytes()) if err != nil { panic("should not error with hardcoded mbase: " + err.Error()) } @@ -324,15 +347,15 @@ 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()) + return mbase.Encode(base, c.Bytes()) default: panic("not possible to reach this point") } @@ -341,60 +364,45 @@ 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()) + 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 { - return c.hash -} +func (c Cid) Hash() mh.Multihash { + bytes := c.Bytes() -// 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 { - case 0: - return c.bytesV0() - case 1: - return c.bytesV1() - default: - panic("not possible to reach this point") + if c.Version() == 0 { + return mh.Multihash(bytes) } -} -func (c *Cid) bytesV0() []byte { - return []byte(c.hash) -} + // skip version length + _, n1 := binary.Uvarint(bytes) + // skip codec length + _, n2 := binary.Uvarint(bytes[n1:]) -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 mh.Multihash(bytes[n1+n2:]) +} - return buf[:n+len(c.hash)] +// 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 { + return []byte(c.str) } // 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 c == o } // UnmarshalJSON parses the JSON representation of a Cid. @@ -405,10 +413,15 @@ func (c *Cid) UnmarshalJSON(b []byte) error { obj := struct { CidTarget string `json:"/"` }{} - err := json.Unmarshal(b, &obj) + objptr := &obj + err := json.Unmarshal(b, &objptr) if err != nil { return err } + if objptr == nil { + *c = Cid{} + return nil + } if obj.CidTarget == "" { return fmt.Errorf("cid was incorrectly formatted") @@ -419,9 +432,8 @@ 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 } @@ -432,30 +444,33 @@ func (c *Cid) UnmarshalJSON(b []byte) error { // 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 casts the result of cid.Bytes() as a string, and returns it. -func (c *Cid) KeyString() string { - return string(c.Bytes()) +// 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{} { +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.Type(), } } @@ -474,10 +489,10 @@ 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 + return Undef, err } switch p.Version { @@ -486,7 +501,7 @@ func (p Prefix) Sum(data []byte) (*Cid, error) { case 1: return NewCidV1(p.Codec, hash), nil default: - return nil, fmt.Errorf("invalid cid version") + return Undef, fmt.Errorf("invalid cid version") } } diff --git a/cid_fuzz.go b/cid_fuzz.go index 357e907..99842b5 100644 --- a/cid_fuzz.go +++ b/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()) diff --git a/cid_test.go b/cid_test.go index 97294c0..1b1e9c4 100644 --- a/cid_test.go +++ b/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.Type() != b.Type() { 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 := NewCidV1(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 := NewCidV1(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 := NewCidV1(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()) diff --git a/package.json b/package.json index 8b821c4..7d9a6c4 100644 --- a/package.json +++ b/package.json @@ -15,9 +15,9 @@ }, { "author": "whyrusleeping", - "hash": "QmSbvata2WqNkqGtZNg8MR3SKwnB8iQ7vTPJgWqB8bC5kR", + "hash": "QmekxXDhCxCJRNuzmHreuaT3BsuJcsjcXWNrtV9C8DRHtd", "name": "go-multibase", - "version": "0.2.7" + "version": "0.3.0" } ], "gxVersion": "0.8.0", @@ -25,6 +25,6 @@ "license": "MIT", "name": "go-cid", "releaseCmd": "git commit -a -m \"gx publish $VERSION\"", - "version": "0.8.0" + "version": "0.9.0" } diff --git a/set.go b/set.go index 7f68657..eb3b3f0 100644 --- a/set.go +++ b/set.go @@ -3,28 +3,28 @@ package cid // Set is a implementation of a set of Cids, that is, a structure // to which holds a single copy of every Cids that is added to it. type Set struct { - set map[string]struct{} + set map[Cid]struct{} } // NewSet initializes and returns a new Set. func NewSet() *Set { - return &Set{set: make(map[string]struct{})} + return &Set{set: make(map[Cid]struct{})} } // Add puts a Cid in the Set. -func (s *Set) Add(c *Cid) { - s.set[string(c.Bytes())] = struct{}{} +func (s *Set) Add(c Cid) { + s.set[c] = struct{}{} } // Has returns if the Set contains a given Cid. -func (s *Set) Has(c *Cid) bool { - _, ok := s.set[string(c.Bytes())] +func (s *Set) Has(c Cid) bool { + _, ok := s.set[c] return ok } // Remove deletes a Cid from the Set. -func (s *Set) Remove(c *Cid) { - delete(s.set, string(c.Bytes())) +func (s *Set) Remove(c Cid) { + delete(s.set, c) } // Len returns how many elements the Set has. @@ -33,18 +33,17 @@ 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) + out = append(out, k) } return out } // 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 @@ -55,9 +54,8 @@ 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 { - for cs := range s.set { - c, _ := Cast([]byte(cs)) +func (s *Set) ForEach(f func(c Cid) error) error { + for c := range s.set { err := f(c) if err != nil { return err @@ -65,4 +63,3 @@ func (s *Set) ForEach(f func(c *Cid) error) error { } return nil } - diff --git a/set_test.go b/set_test.go index 38d7317..fa553d0 100644 --- a/set_test.go +++ b/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") } diff --git a/varint.go b/varint.go new file mode 100644 index 0000000..391c1f4 --- /dev/null +++ b/varint.go @@ -0,0 +1,34 @@ +package cid + +// Version of varint function that work with a string rather than +// []byte to avoid unnecessary allocation + +// Copyright 2011 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license as given at https://golang.org/LICENSE + +// uvarint decodes a uint64 from buf and returns that value and the +// number of characters read (> 0). If an error occurred, the value is 0 +// and the number of bytes n is <= 0 meaning: +// +// n == 0: buf too small +// n < 0: value larger than 64 bits (overflow) +// and -n is the number of bytes read +// +func uvarint(buf string) (uint64, int) { + var x uint64 + var s uint + // we have a binary string so we can't use a range loope + for i := 0; i < len(buf); i++ { + b := buf[i] + if b < 0x80 { + if i > 9 || i == 9 && b > 1 { + return 0, -(i + 1) // overflow + } + return x | uint64(b)<