implement CidFromReader

And reuse two CidFromBytes tests for it, which includes both CIDv0 and
CIDv1 cases as inputs, as well as some inputs that should error.

Fixes #126.

.github/workflows/automerge.yml

@@ -0,0 +1,51 @@
+# File managed by web3-bot. DO NOT EDIT.
+# See https://github.com/protocol/.github/ for details.
+
+# Automatically merge pull requests opened by web3-bot, as soon as (and only if) all tests pass.
+# This reduces the friction associated with updating with our workflows.
+
+on: [ pull_request ]
+name: Automerge
+
+jobs:
+  automerge-check:
+    if: github.event.pull_request.user.login == 'web3-bot'
+    runs-on: ubuntu-latest
+    outputs:
+      status: ${{ steps.should-automerge.outputs.status }}
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        fetch-depth: 0
+    - name: Check if we should automerge
+      id: should-automerge
+      run: |
+        for commit in $(git rev-list --first-parent origin/${{ github.event.pull_request.base.ref }}..${{ github.event.pull_request.head.sha }}); do
+          committer=$(git show --format=$'%ce' -s $commit)
+          echo "Committer: $committer"
+          if [[ "$committer" != "web3-bot@users.noreply.github.com" ]]; then
+            echo "Commit $commit wasn't committed by web3-bot, but by $committer."
+            echo "::set-output name=status::false"
+            exit
+          fi
+        done
+        echo "::set-output name=status::true"
+  automerge:
+    needs: automerge-check
+    runs-on: ubuntu-latest
+    if: ${{ needs.automerge-check.outputs.status == 'true' }}
+    steps:
+    - name: Wait on tests
+      uses: lewagon/wait-on-check-action@bafe56a6863672c681c3cf671f5e10b20abf2eaa # v0.2
+      with:
+        ref: ${{ github.event.pull_request.head.sha }}
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        wait-interval: 10
+        running-workflow-name: 'automerge' # the name of this job
+    - name: Merge PR
+      uses: pascalgn/automerge-action@741c311a47881be9625932b0a0de1b0937aab1ae # v0.13.1
+      env:
+        GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+        MERGE_LABELS: ""
+        MERGE_METHOD: "squash"
+        MERGE_DELETE_BRANCH: true

.github/workflows/go-check.yml

@@ -0,0 +1,50 @@
+# File managed by web3-bot. DO NOT EDIT.
+# See https://github.com/protocol/.github/ for details.
+
+on: [push, pull_request]
+name: Go Checks
+
+jobs:
+  unit:
+    runs-on: ubuntu-latest
+    name: All
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          submodules: recursive
+      - uses: actions/setup-go@v2
+        with:
+          go-version: "1.16.x"
+      - name: Install staticcheck
+        run: go install honnef.co/go/tools/cmd/staticcheck@434f5f3816b358fe468fa83dcba62d794e7fe04b # 2021.1 (v0.2.0)
+      - name: Check that go.mod is tidy
+        uses: protocol/multiple-go-modules@v1.0
+        with:
+          run: |
+            go mod tidy
+            if [[ -n $(git ls-files --other --exclude-standard --directory -- go.sum) ]]; then
+              echo "go.sum was added by go mod tidy"
+              exit 1
+            fi
+            git diff --exit-code -- go.sum go.mod
+      - name: gofmt
+        if: ${{ success() || failure() }} # run this step even if the previous one failed
+        run: |
+          out=$(gofmt -s -l .)
+          if [[ -n "$out" ]]; then
+            echo $out | awk '{print "::error file=" $0 ",line=0,col=0::File is not gofmt-ed."}'
+            exit 1
+          fi
+      - name: go vet
+        if: ${{ success() || failure() }} # run this step even if the previous one failed
+        uses: protocol/multiple-go-modules@v1.0
+        with:
+          run: go vet ./...
+      - name: staticcheck
+        if: ${{ success() || failure() }} # run this step even if the previous one failed
+        uses: protocol/multiple-go-modules@v1.0
+        with:
+          run: |
+            set -o pipefail
+            staticcheck ./... | sed -e 's@\(.*\)\.go@./\1.go@g'
+

.github/workflows/go-test.yml

@@ -0,0 +1,47 @@
+# File managed by web3-bot. DO NOT EDIT.
+# See https://github.com/protocol/.github/ for details.
+
+on: [push, pull_request]
+name: Go Test
+
+jobs:
+  unit:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ "ubuntu", "windows", "macos" ]
+        go: [ "1.15.x", "1.16.x" ]
+    runs-on: ${{ matrix.os }}-latest
+    name: ${{ matrix.os}} (go ${{ matrix.go }})
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          submodules: recursive
+      - uses: actions/setup-go@v2
+        with:
+          go-version: ${{ matrix.go }}
+      - name: Go information
+        run: |
+          go version
+          go env
+      - name: Run tests
+        uses: protocol/multiple-go-modules@v1.0
+        with:
+          run: go test -v -coverprofile coverage.txt ./...
+      - name: Run tests (32 bit)
+        if: ${{ matrix.os != 'macos' }} # can't run 32 bit tests on OSX.
+        uses: protocol/multiple-go-modules@v1.0
+        env:
+          GOARCH: 386
+        with:
+          run: go test -v ./...
+      - name: Run tests with race detector
+        if: ${{ matrix.os == 'ubuntu' }} # speed things up. Windows and OSX VMs are slow
+        uses: protocol/multiple-go-modules@v1.0
+        with:
+          run: go test -v -race ./...
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@a1ed4b322b4b38cb846afb5a0ebfa17086917d27 # v1.5.0
+        with:
+          file: coverage.txt
+          env_vars: OS=${{ matrix.os }}, GO=${{ matrix.go }}

.travis.yml

@@ -1,30 +0,0 @@
-os:
-  - linux
-
-language: go
-
-go:
-  - 1.11.x
-
-env:
-  global:
-    - GOTFLAGS="-race"
-  matrix:
-    - BUILD_DEPTYPE=gomod
-
-
-# disable travis install
-install:
-  - true
-
-script:
-  - bash <(curl -s https://raw.githubusercontent.com/ipfs/ci-helpers/master/travis-ci/run-standard-tests.sh)
-
-
-cache:
-  directories:
-    - $GOPATH/pkg/mod
-    - $HOME/.cache/go-build
-
-notifications:
-  email: false

builder_test.go

@@ -65,9 +65,29 @@ func TestCodecChange(t *testing.T) {
 		p := Prefix{Version: 1, Codec: DagProtobuf, MhType: mh.SHA2_256, MhLength: mh.DefaultLengths[mh.SHA2_256]}
 		testCodecChange(t, p)
 	})
+	t.Run("Prefix-NoChange", func(t *testing.T) {
+		p := Prefix{Version: 0, Codec: DagProtobuf, MhType: mh.SHA2_256, MhLength: mh.DefaultLengths[mh.SHA2_256]}
+		if p.GetCodec() != DagProtobuf {
+			t.Fatal("original builder not using Protobuf codec")
+		}
+		pn := p.WithCodec(DagProtobuf)
+		if pn != p {
+			t.Fatal("should have returned same builder")
+		}
+	})
 	t.Run("V0Builder", func(t *testing.T) {
 		testCodecChange(t, V0Builder{})
 	})
+	t.Run("V0Builder-NoChange", func(t *testing.T) {
+		b := V0Builder{}
+		if b.GetCodec() != DagProtobuf {
+			t.Fatal("original builder not using Protobuf codec")
+		}
+		bn := b.WithCodec(DagProtobuf)
+		if bn != b {
+			t.Fatal("should have returned same builder")
+		}
+	})
 	t.Run("V1Builder", func(t *testing.T) {
 		testCodecChange(t, V1Builder{Codec: DagProtobuf, MhType: mh.SHA2_256})
 	})

cid.go

@@ -58,6 +58,7 @@ const (
 
 	GitRaw = 0x78
 
+	DagJOSE               = 0x85
 	EthBlock              = 0x90
 	EthBlockList          = 0x91
 	EthTxTrie             = 0x92
@@ -106,6 +107,7 @@ var Codecs = map[string]uint64{
 	"dash-tx":                 DashTx,
 	"fil-commitment-unsealed": FilCommitmentUnsealed,
 	"fil-commitment-sealed":   FilCommitmentSealed,
+	"dag-jose":                DagJOSE,
 }
 
 // CodecToStr maps the numeric codec to its name
@@ -133,6 +135,7 @@ var CodecToStr = map[uint64]string{
 	DashTx:                "dash-tx",
 	FilCommitmentUnsealed: "fil-commitment-unsealed",
 	FilCommitmentSealed:   "fil-commitment-sealed",
+	DagJOSE:               "dag-jose",
 }
 
 // tryNewCidV0 tries to convert a multihash into a CIDv0 CID and returns an
@@ -182,10 +185,12 @@ func NewCidV1(codecType uint64, mhash mh.Multihash) Cid {
 	return Cid{string(buf[:n+hashlen])}
 }
 
-var _ encoding.BinaryMarshaler = Cid{}
-var _ encoding.BinaryUnmarshaler = (*Cid)(nil)
-var _ encoding.TextMarshaler = Cid{}
-var _ encoding.TextUnmarshaler = (*Cid)(nil)
+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
@@ -561,7 +566,7 @@ type Prefix struct {
 // 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.ID {
+	if p.MhType == mh.IDENTITY {
 		length = -1
 	}
 
@@ -675,3 +680,139 @@ func CidFromBytes(data []byte) (int, Cid, error) {
 
 	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.
+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 {
+		return len(br.dst), Undef, 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, err
+		}
+
+		br.dst = br.dst[:34]
+		h, err := mh.Cast(br.dst)
+		if err != nil {
+			return len(br.dst), Undef, err
+		}
+
+		return len(br.dst), Cid{string(h)}, nil
+	}
+
+	if vers != 1 {
+		return len(br.dst), Undef, 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, 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, err
+	}
+
+	// Multihash digest length.
+	mhl, err := varint.ReadUvarint(br)
+	if err != nil {
+		return len(br.dst), Undef, 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, 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-cap(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, 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, err
+	}
+
+	return len(br.dst), Cid{string(br.dst)}, nil
+}

cid_fuzz.go

@@ -4,7 +4,6 @@ package cid
 
 func Fuzz(data []byte) int {
 	cid, err := Cast(data)
-
 	if err != nil {
 		return 0
 	}

cid_test.go

@@ -4,9 +4,12 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"io"
 	"math/rand"
+	"reflect"
 	"strings"
 	"testing"
+	"testing/iotest"
 
 	mbase "github.com/multiformats/go-multibase"
 	mh "github.com/multiformats/go-multihash"
@@ -40,6 +43,7 @@ var tCodecs = map[uint64]string{
 	DashTx:                "dash-tx",
 	FilCommitmentUnsealed: "fil-commitment-unsealed",
 	FilCommitmentSealed:   "fil-commitment-sealed",
+	DagJOSE:               "dag-jose",
 }
 
 func assertEqual(t *testing.T, a, b Cid) {
@@ -80,7 +84,7 @@ func TestPrefixSum(t *testing.T) {
 	// Test creating CIDs both manually and with Prefix.
 	// Tests: https://github.com/ipfs/go-cid/issues/83
 	for _, hashfun := range []uint64{
-		mh.ID, mh.SHA3, mh.SHA2_256,
+		mh.IDENTITY, mh.SHA3, mh.SHA2_256,
 	} {
 		h1, err := mh.Sum([]byte("TEST"), hashfun, -1)
 		if err != nil {
@@ -184,8 +188,32 @@ func TestBasesMarshaling(t *testing.T) {
 		}
 		s2 := cid.Encode(encoder)
 		if s != s2 {
-			t.Fatalf("'%s' != '%s'", s, s2)
+			t.Fatalf("%q != %q", s, s2)
 		}
+
+		ee, err := ExtractEncoding(s)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if ee != b {
+			t.Fatalf("could not properly determine base (got %v)", ee)
+		}
+	}
+
+	ee, err := ExtractEncoding("QmdfTbBqBPQ7VNxZEYEj14VmRuZBkqFbiwReogJgS1zR1n")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if ee != mbase.Base58BTC {
+		t.Fatalf("expected Base58BTC from Qm string (got %v)", ee)
+	}
+
+	ee, err = ExtractEncoding("1")
+	if err == nil {
+		t.Fatal("expected too-short error from ExtractEncoding")
+	}
+	if ee != -1 {
+		t.Fatal("expected -1 from too-short ExtractEncoding")
 	}
 }
 
@@ -194,18 +222,32 @@ func TestBinaryMarshaling(t *testing.T) {
 	hash, _ := mh.Sum(data, mh.SHA2_256, -1)
 	c := NewCidV1(DagCBOR, hash)
 	var c2 Cid
+	var c3 Cid
 
 	data, err := c.MarshalBinary()
 	if err != nil {
 		t.Fatal(err)
 	}
-	err = c2.UnmarshalBinary(data)
-	if err != nil {
+	if err = c2.UnmarshalBinary(data); err != nil {
 		t.Fatal(err)
 	}
 	if !c.Equals(c2) {
 		t.Errorf("cids should be the same: %s %s", c, c2)
 	}
+	var buf bytes.Buffer
+	wrote, err := c.WriteBytes(&buf)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if wrote != 36 {
+		t.Fatalf("expected 36 bytes written (got %d)", wrote)
+	}
+	if err = c3.UnmarshalBinary(data); err != nil {
+		t.Fatal(err)
+	}
+	if !c.Equals(c3) {
+		t.Errorf("cids should be the same: %s %s", c, c3)
+	}
 }
 
 func TestTextMarshaling(t *testing.T) {
@@ -218,13 +260,16 @@ func TestTextMarshaling(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	err = c2.UnmarshalText(data)
-	if err != nil {
+	if err = c2.UnmarshalText(data); err != nil {
 		t.Fatal(err)
 	}
 	if !c.Equals(c2) {
 		t.Errorf("cids should be the same: %s %s", c, c2)
 	}
+
+	if c.KeyString() != string(c.Bytes()) {
+		t.Errorf("got unexpected KeyString() result")
+	}
 }
 
 func TestEmptyString(t *testing.T) {
@@ -254,6 +299,11 @@ func TestV0Handling(t *testing.T) {
 		t.Fatal("marshaling roundtrip failed")
 	}
 
+	byteLen := cid.ByteLen()
+	if byteLen != 34 {
+		t.Fatalf("expected V0 ByteLen to be 34 (got %d)", byteLen)
+	}
+
 	new, err := cid.StringOfBase(mbase.Base58BTC)
 	if err != nil {
 		t.Fatal(err)
@@ -269,6 +319,11 @@ func TestV0Handling(t *testing.T) {
 	if cid.Encode(encoder) != old {
 		t.Fatal("Encode roundtrip failed")
 	}
+
+	_, err = cid.StringOfBase(mbase.Base32)
+	if err != ErrInvalidEncoding {
+		t.Fatalf("expected ErrInvalidEncoding for V0 StringOfBase(Base32) (got %v)", err)
+	}
 }
 
 func TestV0ErrorCases(t *testing.T) {
@@ -335,7 +390,6 @@ func TestNewPrefixV0(t *testing.T) {
 	if c1.Prefix() != c2.Prefix() {
 		t.Fatal("prefixes mismatch")
 	}
-
 }
 
 func TestInvalidV0Prefix(t *testing.T) {
@@ -369,7 +423,14 @@ func TestInvalidV0Prefix(t *testing.T) {
 			t.Fatalf("should error (index %d)", i)
 		}
 	}
+}
 
+func TestBadPrefix(t *testing.T) {
+	p := Prefix{Version: 3, Codec: DagProtobuf, MhType: mh.SHA2_256, MhLength: 3}
+	_, err := p.Sum([]byte{0x00, 0x01, 0x03})
+	if err == nil {
+		t.Fatalf("expected error on v3 prefix Sum")
+	}
 }
 
 func TestPrefixRoundtrip(t *testing.T) {
@@ -401,6 +462,25 @@ func TestPrefixRoundtrip(t *testing.T) {
 	}
 }
 
+func TestBadPrefixFromBytes(t *testing.T) {
+	_, err := PrefixFromBytes([]byte{0x80})
+	if err == nil {
+		t.Fatal("expected error for bad byte 0")
+	}
+	_, err = PrefixFromBytes([]byte{0x01, 0x80})
+	if err == nil {
+		t.Fatal("expected error for bad byte 1")
+	}
+	_, err = PrefixFromBytes([]byte{0x01, 0x01, 0x80})
+	if err == nil {
+		t.Fatal("expected error for bad byte 2")
+	}
+	_, err = PrefixFromBytes([]byte{0x01, 0x01, 0x01, 0x80})
+	if err == nil {
+		t.Fatal("expected error for bad byte 3")
+	}
+}
+
 func Test16BytesVarint(t *testing.T) {
 	data := []byte("this is some test content")
 	hash, _ := mh.Sum(data, mh.SHA2_256, -1)
@@ -433,13 +513,13 @@ func TestParse(t *testing.T) {
 	}
 
 	assertions := [][]interface{}{
-		[]interface{}{NewCidV0(h), theHash},
-		[]interface{}{NewCidV0(h).Bytes(), theHash},
-		[]interface{}{h, theHash},
-		[]interface{}{theHash, theHash},
-		[]interface{}{"/ipfs/" + theHash, theHash},
-		[]interface{}{"https://ipfs.io/ipfs/" + theHash, theHash},
-		[]interface{}{"http://localhost:8080/ipfs/" + theHash, theHash},
+		{NewCidV0(h), theHash},
+		{NewCidV0(h).Bytes(), theHash},
+		{h, theHash},
+		{theHash, theHash},
+		{"/ipfs/" + theHash, theHash},
+		{"https://ipfs.io/ipfs/" + theHash, theHash},
+		{"http://localhost:8080/ipfs/" + theHash, theHash},
 	}
 
 	assert := func(arg interface{}, expected string) error {
@@ -448,7 +528,7 @@ func TestParse(t *testing.T) {
 			return err
 		}
 		if cid.Version() != 0 {
-			return fmt.Errorf("expected version 0, got %s", string(cid.Version()))
+			return fmt.Errorf("expected version 0, got %d", cid.Version())
 		}
 		actual := cid.Hash().B58String()
 		if actual != expected {
@@ -462,8 +542,7 @@ func TestParse(t *testing.T) {
 	}
 
 	for _, args := range assertions {
-		err := assert(args[0], args[1].(string))
-		if err != nil {
+		if err := assert(args[0], args[1].(string)); err != nil {
 			t.Fatal(err)
 		}
 	}
@@ -497,8 +576,7 @@ func TestFromJson(t *testing.T) {
 	cval := "bafkreie5qrjvaw64n4tjm6hbnm7fnqvcssfed4whsjqxzslbd3jwhsk3mm"
 	jsoncid := []byte(`{"/":"` + cval + `"}`)
 	var c Cid
-	err := json.Unmarshal(jsoncid, &c)
-	if err != nil {
+	if err := json.Unmarshal(jsoncid, &c); err != nil {
 		t.Fatal(err)
 	}
 
@@ -508,6 +586,7 @@ func TestFromJson(t *testing.T) {
 }
 
 func TestJsonRoundTrip(t *testing.T) {
+	expectedJSON := `{"/":"bafkreie5qrjvaw64n4tjm6hbnm7fnqvcssfed4whsjqxzslbd3jwhsk3mm"}`
 	exp, err := Decode("bafkreie5qrjvaw64n4tjm6hbnm7fnqvcssfed4whsjqxzslbd3jwhsk3mm")
 	if err != nil {
 		t.Fatal(err)
@@ -519,21 +598,50 @@ func TestJsonRoundTrip(t *testing.T) {
 		t.Fatal(err)
 	}
 	var actual Cid
-	err = json.Unmarshal(enc, &actual)
+	if err = json.Unmarshal(enc, &actual); err != nil {
+		t.Fatal(err)
+	}
 	if !exp.Equals(actual) {
 		t.Fatal("cids not equal for *Cid")
 	}
 
+	if string(enc) != expectedJSON {
+		t.Fatalf("did not get expected JSON form (got %q)", string(enc))
+	}
+
 	// Verify it works for a Cid.
 	enc, err = json.Marshal(exp)
 	if err != nil {
 		t.Fatal(err)
 	}
 	var actual2 Cid
-	err = json.Unmarshal(enc, &actual2)
+	if err = json.Unmarshal(enc, &actual2); err != nil {
+		t.Fatal(err)
+	}
 	if !exp.Equals(actual2) {
 		t.Fatal("cids not equal for Cid")
 	}
+
+	if err = actual2.UnmarshalJSON([]byte("1")); err == nil {
+		t.Fatal("expected error for too-short JSON")
+	}
+
+	if err = actual2.UnmarshalJSON([]byte(`{"nope":"nope"}`)); err == nil {
+		t.Fatal("expected error for bad CID JSON")
+	}
+
+	if err = actual2.UnmarshalJSON([]byte(`bad "" json!`)); err == nil {
+		t.Fatal("expected error for bad JSON")
+	}
+
+	var actual3 Cid
+	enc, err = actual3.MarshalJSON()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(enc) != "null" {
+		t.Fatalf("expected 'null' string for undefined CID (got %q)", string(enc))
+	}
 }
 
 func BenchmarkStringV1(b *testing.B) {
@@ -586,6 +694,99 @@ func TestReadCidsFromBuffer(t *testing.T) {
 	if cur != len(buf) {
 		t.Fatal("had trailing bytes")
 	}
+
+	// The same, but now with CidFromReader.
+	// In multiple forms, to catch more io interface bugs.
+	for _, r := range []io.Reader{
+		// implements io.ByteReader
+		bytes.NewReader(buf),
+
+		// tiny reads, no io.ByteReader
+		iotest.OneByteReader(bytes.NewReader(buf)),
+	} {
+		cur = 0
+		for _, expc := range cids {
+			n, c, err := CidFromReader(r)
+			if err != nil {
+				t.Fatal(err)
+			}
+			if c != expc {
+				t.Fatal("cids mismatched")
+			}
+			cur += n
+		}
+		if cur != len(buf) {
+			t.Fatal("had trailing bytes")
+		}
+	}
+}
+
+func TestBadCidInput(t *testing.T) {
+	for _, name := range []string{
+		"FromBytes",
+		"FromReader",
+	} {
+		t.Run(name, func(t *testing.T) {
+			usingReader := name == "FromReader"
+
+			fromBytes := CidFromBytes
+			if usingReader {
+				fromBytes = func(data []byte) (int, Cid, error) {
+					return CidFromReader(bytes.NewReader(data))
+				}
+			}
+
+			l, c, err := fromBytes([]byte{mh.SHA2_256, 32, 0x00})
+			if err == nil {
+				t.Fatal("expected not-enough-bytes for V0 CID")
+			}
+			if !usingReader && l != 0 {
+				t.Fatal("expected length==0 from bad CID")
+			} else if usingReader && l == 0 {
+				t.Fatal("expected length!=0 from bad CID")
+			}
+			if c != Undef {
+				t.Fatal("expected Undef CID from bad CID")
+			}
+
+			c, err = Decode("bafkreie5qrjvaw64n4tjm6hbnm7fnqvcssfed4whsjqxzslbd3jwhsk3mm")
+			if err != nil {
+				t.Fatal(err)
+			}
+			byts := make([]byte, c.ByteLen())
+			copy(byts, c.Bytes())
+			byts[1] = 0x80 // bad codec varint
+			byts[2] = 0x00
+			l, c, err = fromBytes(byts)
+			if err == nil {
+				t.Fatal("expected not-enough-bytes for V1 CID")
+			}
+			if !usingReader && l != 0 {
+				t.Fatal("expected length==0 from bad CID")
+			} else if usingReader && l == 0 {
+				t.Fatal("expected length!=0 from bad CID")
+			}
+			if c != Undef {
+				t.Fatal("expected Undef CID from bad CID")
+			}
+
+			copy(byts, c.Bytes())
+			byts[2] = 0x80 // bad multihash varint
+			byts[3] = 0x00
+			l, c, err = fromBytes(byts)
+			if err == nil {
+				t.Fatal("expected not-enough-bytes for V1 CID")
+			}
+			if !usingReader && l != 0 {
+				t.Fatal("expected length==0 from bad CID")
+			} else if usingReader && l == 0 {
+				t.Fatal("expected length!=0 from bad CID")
+			}
+			if c != Undef {
+				t.Fatal("expected Undef CID from bad CidFromBytes")
+			}
+		})
+	}
 }
 
 func TestBadParse(t *testing.T) {
@@ -598,3 +799,16 @@ func TestBadParse(t *testing.T) {
 		t.Fatal("expected to fail to parse an invalid CIDv1 CID")
 	}
 }
+
+func TestLoggable(t *testing.T) {
+	c, err := Decode("bafkreie5qrjvaw64n4tjm6hbnm7fnqvcssfed4whsjqxzslbd3jwhsk3mm")
+	if err != nil {
+		t.Fatal(err)
+	}
+	actual := c.Loggable()
+	expected := make(map[string]interface{})
+	expected["cid"] = c
+	if !reflect.DeepEqual(actual, expected) {
+		t.Fatalf("did not get expected loggable form (got %v)", actual)
+	}
+}

go.mod

@@ -2,8 +2,9 @@ module github.com/ipfs/go-cid
 
 require (
 	github.com/multiformats/go-multibase v0.0.3
-	github.com/multiformats/go-multihash v0.0.13
-	github.com/multiformats/go-varint v0.0.5
+	github.com/multiformats/go-multihash v0.0.15
+	github.com/multiformats/go-varint v0.0.6
+	golang.org/x/crypto v0.0.0-20210506145944-38f3c27a63bf // indirect
 )
 
-go 1.13
+go 1.15

go.sum

@@ -1,28 +1,35 @@
+github.com/klauspost/cpuid/v2 v2.0.4 h1:g0I61F2K2DjRHz1cnxlkNSBIaePVoJIjjnHui8QHbiw=
+github.com/klauspost/cpuid/v2 v2.0.4/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1 h1:lYpkrQH5ajf0OXOcUbGjvZxxijuBwbbmlSxLiuofa+g=
 github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1/go.mod h1:pD8RvIylQ358TN4wwqatJ8rNavkEINozVn9DtGI3dfQ=
-github.com/minio/sha256-simd v0.1.1-0.20190913151208-6de447530771 h1:MHkK1uRtFbVqvAgvWxafZe54+5uBxLluGylDiKgdhwo=
-github.com/minio/sha256-simd v0.1.1-0.20190913151208-6de447530771/go.mod h1:B5e1o+1/KgNmWrSQK08Y6Z1Vb5pwIktudl0J58iy0KM=
-github.com/mr-tron/base58 v1.1.0 h1:Y51FGVJ91WBqCEabAi5OPUz38eAx8DakuAm5svLcsfQ=
+github.com/minio/sha256-simd v1.0.0 h1:v1ta+49hkWZyvaKwrQB8elexRqm6Y0aMLjCNsrYxo6g=
+github.com/minio/sha256-simd v1.0.0/go.mod h1:OuYzVNI5vcoYIAmbIvHPl3N3jUzVedXbKy5RFepssQM=
 github.com/mr-tron/base58 v1.1.0/go.mod h1:xcD2VGqlgYjBdcBLw+TuYLr8afG+Hj8g2eTVqeSzSU8=
-github.com/mr-tron/base58 v1.1.3 h1:v+sk57XuaCKGXpWtVBX8YJzO7hMGx4Aajh4TQbdEFdc=
-github.com/mr-tron/base58 v1.1.3/go.mod h1:BinMc/sQntlIE1frQmRFPUoPA1Zkr8VRgBdjWI2mNwc=
+github.com/mr-tron/base58 v1.2.0 h1:T/HDJBh4ZCPbU39/+c3rRvE0uKBQlU27+QI8LJ4t64o=
+github.com/mr-tron/base58 v1.2.0/go.mod h1:BinMc/sQntlIE1frQmRFPUoPA1Zkr8VRgBdjWI2mNwc=
 github.com/multiformats/go-base32 v0.0.3 h1:tw5+NhuwaOjJCC5Pp82QuXbrmLzWg7uxlMFp8Nq/kkI=
 github.com/multiformats/go-base32 v0.0.3/go.mod h1:pLiuGC8y0QR3Ue4Zug5UzK9LjgbkL8NSQj0zQ5Nz/AA=
 github.com/multiformats/go-base36 v0.1.0 h1:JR6TyF7JjGd3m6FbLU2cOxhC0Li8z8dLNGQ89tUg4F4=
 github.com/multiformats/go-base36 v0.1.0/go.mod h1:kFGE83c6s80PklsHO9sRn2NCoffoRdUUOENyW/Vv6sM=
 github.com/multiformats/go-multibase v0.0.3 h1:l/B6bJDQjvQ5G52jw4QGSYeOTZoAwIO77RblWplfIqk=
 github.com/multiformats/go-multibase v0.0.3/go.mod h1:5+1R4eQrT3PkYZ24C3W2Ue2tPwIdYQD509ZjSb5y9Oc=
-github.com/multiformats/go-multihash v0.0.13 h1:06x+mk/zj1FoMsgNejLpy6QTvJqlSt/BhLEy87zidlc=
-github.com/multiformats/go-multihash v0.0.13/go.mod h1:VdAWLKTwram9oKAatUcLxBNUjdtcVwxObEQBtRfuyjc=
-github.com/multiformats/go-varint v0.0.5 h1:XVZwSo04Cs3j/jS0uAEPpT3JY6DzMcVLLoWOSnCxOjg=
-github.com/multiformats/go-varint v0.0.5/go.mod h1:3Ls8CIEsrijN6+B7PbrXRPxHRPuXSrVKRY101jdMZYE=
-github.com/spaolacci/murmur3 v1.1.0 h1:7c1g84S4BPRrfL5Xrdp6fOJ206sU9y293DDHaoy0bLI=
-github.com/spaolacci/murmur3 v1.1.0/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA=
+github.com/multiformats/go-multihash v0.0.15 h1:hWOPdrNqDjwHDx82vsYGSDZNyktOJJ2dzZJzFkOV1jM=
+github.com/multiformats/go-multihash v0.0.15/go.mod h1:D6aZrWNLFTV/ynMpKsNtB40mJzmCl4jb1alC0OvHiHg=
+github.com/multiformats/go-varint v0.0.6 h1:gk85QWKxh3TazbLxED/NlDVv8+q+ReFJk7Y2W/KhfNY=
+github.com/multiformats/go-varint v0.0.6/go.mod h1:3Ls8CIEsrijN6+B7PbrXRPxHRPuXSrVKRY101jdMZYE=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/crypto v0.0.0-20190611184440-5c40567a22f8 h1:1wopBVtVdWnn03fZelqdXTqk7U7zPQCb+T4rbU9ZEoU=
-golang.org/x/crypto v0.0.0-20190611184440-5c40567a22f8/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20210220033148-5ea612d1eb83/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
+golang.org/x/crypto v0.0.0-20210506145944-38f3c27a63bf h1:B2n+Zi5QeYRDAEodEu72OS36gmTWjgpXr2+cWcBW90o=
+golang.org/x/crypto v0.0.0-20210506145944-38f3c27a63bf/go.mod h1:P+XmwS30IXTQdn5tA2iutPOUgjI07+tq3H3K9MVA1s8=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190412213103-97732733099d h1:+R4KGOnez64A81RvjARKc4UT5/tI9ujCIVX+P5KiHuI=
-golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210309074719-68d13333faf2 h1:46ULzRKLh1CwgRq2dC5SlBzEqqNCi8rreOZnNrbqcIY=
+golang.org/x/sys v0.0.0-20210309074719-68d13333faf2/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

varint.go

@@ -4,7 +4,7 @@ import (
 	"github.com/multiformats/go-varint"
 )
 
-// Version of varint function that work with a string rather than
+// Version of varint function that works with a string rather than
 // []byte to avoid unnecessary allocation
 
 // Copyright 2011 The Go Authors. All rights reserved.
@@ -12,23 +12,20 @@ import (
 // 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
-//
+// number of bytes read (> 0). If an error occurred, then 0 is
+// returned for both the value and the number of bytes read, and an
+// error is returned.
 func uvarint(buf string) (uint64, int, error) {
 	var x uint64
 	var s uint
-	// we have a binary string so we can't use a range loope
+	// we have a binary string so we can't use a range loop
 	for i := 0; i < len(buf); i++ {
 		b := buf[i]
 		if b < 0x80 {
 			if i > 9 || i == 9 && b > 1 {
 				return 0, 0, varint.ErrOverflow
-			} else if b == 0 && i > 0 {
+			}
+			if b == 0 && i > 0 {
 				return 0, 0, varint.ErrNotMinimal
 			}
 			return x | uint64(b)<<s, i + 1, nil

varint_test.go

@@ -28,3 +28,29 @@ func TestUvarintRoundTrip(t *testing.T) {
 		}
 	}
 }
+
+func TestUvarintEdges(t *testing.T) {
+	tests := []struct {
+		name  string
+		input []byte
+		want  error
+	}{
+		{"ErrNotMinimal", []byte{0x01 | 0x80, 0}, varint.ErrNotMinimal},
+		{"ErrOverflow", []byte{0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x01}, varint.ErrOverflow},
+		{"ErrUnderflow", []byte{0x80}, varint.ErrUnderflow},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			v, l1, err := uvarint(string(test.input))
+			if err != test.want {
+				t.Fatalf("error case (%v) should return varint.%s (got: %v)", test.input, test.name, err)
+			}
+			if v != 0 {
+				t.Fatalf("error case (%v) should return 0 value (got %d)", test.input, v)
+			}
+			if l1 != 0 {
+				t.Fatalf("error case (%v) should return 0 length (got %d)", test.input, l1)
+			}
+		})
+	}
+}