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

@@ -1,11 +1,51 @@
 # File managed by web3-bot. DO NOT EDIT.
 # See https://github.com/protocol/.github/ for details.
 
-name: Automerge
+# 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:
-    uses: protocol/.github/.github/workflows/automerge.yml@master
+    needs: automerge-check
-    with:
+    runs-on: ubuntu-latest
-      job: 'automerge'
+    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

@@ -8,28 +8,17 @@ jobs:
   unit:
     runs-on: ubuntu-latest
     name: All
-    env:
-      RUNGOGENERATE: false
     steps:
       - uses: actions/checkout@v2
         with:
           submodules: recursive
       - uses: actions/setup-go@v2
         with:
-          go-version: "1.18.x"
+          go-version: "1.16.x"
-      - name: Run repo-specific setup
-        uses: ./.github/actions/go-check-setup
-        if: hashFiles('./.github/actions/go-check-setup') != ''
-      - name: Read config
-        if: hashFiles('./.github/workflows/go-check-config.json') != ''
-        run: |
-          if jq -re .gogenerate ./.github/workflows/go-check-config.json; then
-            echo "RUNGOGENERATE=true" >> $GITHUB_ENV
-          fi
       - name: Install staticcheck
-        run: go install honnef.co/go/tools/cmd/staticcheck@d7e217c1ff411395475b2971c0824e1e7cc1af98 # 2022.1 (v0.3.0)
+        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@v1.2
+        uses: protocol/multiple-go-modules@v1.0
         with:
           run: |
             go mod tidy
@@ -48,26 +37,14 @@ jobs:
           fi
       - name: go vet
         if: ${{ success() || failure() }} # run this step even if the previous one failed
-        uses: protocol/multiple-go-modules@v1.2
+        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@v1.2
+        uses: protocol/multiple-go-modules@v1.0
         with:
           run: |
             set -o pipefail
             staticcheck ./... | sed -e 's@\(.*\)\.go@./\1.go@g'
-      - name: go generate
+
-        uses: protocol/multiple-go-modules@v1.2
-        if: (success() || failure()) && env.RUNGOGENERATE == 'true'
-        with:
-          run: |
-            git clean -fd # make sure there aren't untracked files / directories
-            go generate ./...
-            # check if go generate modified or added any files
-            if ! $(git add . && git diff-index HEAD --exit-code --quiet); then
-              echo "go generated caused changes to the repository:"
-              git status --short
-              exit 1
-            fi

.github/workflows/go-test.yml

@@ -10,11 +10,9 @@ jobs:
       fail-fast: false
       matrix:
         os: [ "ubuntu", "windows", "macos" ]
-        go: [ "1.17.x", "1.18.x" ]
+        go: [ "1.15.x", "1.16.x" ]
-    env:
+    runs-on: ${{ matrix.os }}-latest
-      COVERAGES: ""
+    name: ${{ matrix.os}} (go ${{ matrix.go }})
-    runs-on: ${{ format('{0}-latest', matrix.os) }}
-    name: ${{ matrix.os }} (go ${{ matrix.go }})
     steps:
       - uses: actions/checkout@v2
         with:
@@ -26,43 +24,24 @@ jobs:
         run: |
           go version
           go env
-      - name: Use msys2 on windows
-        if: ${{ matrix.os == 'windows' }}
-        shell: bash
-        # The executable for msys2 is also called bash.cmd
-        #   https://github.com/actions/virtual-environments/blob/main/images/win/Windows2019-Readme.md#shells
-        # If we prepend its location to the PATH
-        #   subsequent 'shell: bash' steps will use msys2 instead of gitbash
-        run: echo "C:/msys64/usr/bin" >> $GITHUB_PATH
-      - name: Run repo-specific setup
-        uses: ./.github/actions/go-test-setup
-        if: hashFiles('./.github/actions/go-test-setup') != ''
       - name: Run tests
-        uses: protocol/multiple-go-modules@v1.2
+        uses: protocol/multiple-go-modules@v1.0
         with:
-          # Use -coverpkg=./..., so that we include cross-package coverage.
+          run: go test -v -coverprofile coverage.txt ./...
-          # If package ./A imports ./B, and ./A's tests also cover ./B,
-          # this means ./B's coverage will be significantly higher than 0%.
-          run: go test -v -coverprofile=module-coverage.txt -coverpkg=./... ./...
       - name: Run tests (32 bit)
         if: ${{ matrix.os != 'macos' }} # can't run 32 bit tests on OSX.
-        uses: protocol/multiple-go-modules@v1.2
+        uses: protocol/multiple-go-modules@v1.0
         env:
           GOARCH: 386
         with:
-          run: |
+          run: go test -v ./...
-            export "PATH=${{ env.PATH_386 }}:$PATH"
-            go test -v ./...
       - name: Run tests with race detector
         if: ${{ matrix.os == 'ubuntu' }} # speed things up. Windows and OSX VMs are slow
-        uses: protocol/multiple-go-modules@v1.2
+        uses: protocol/multiple-go-modules@v1.0
         with:
           run: go test -v -race ./...
-      - name: Collect coverage files
-        shell: bash
-        run: echo "COVERAGES=$(find . -type f -name 'module-coverage.txt' | tr -s '\n' ',' | sed 's/,$//')" >> $GITHUB_ENV
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@f32b3a3741e1053eb607407145bc9619351dc93b # v2.1.0
+        uses: codecov/codecov-action@a1ed4b322b4b38cb846afb5a0ebfa17086917d27 # v1.5.0
         with:
-          files: '${{ env.COVERAGES }}'
+          file: coverage.txt
           env_vars: OS=${{ matrix.os }}, GO=${{ matrix.go }}

.github/workflows/release-check.yml

@@ -1,11 +0,0 @@
-# File managed by web3-bot. DO NOT EDIT.
-# See https://github.com/protocol/.github/ for details.
-
-name: Release Checker
-on:
-  pull_request:
-    paths: [ 'version.json' ]
-
-jobs:
-  release-check:
-    uses: protocol/.github/.github/workflows/release-check.yml@master

.github/workflows/releaser.yml

@@ -1,11 +0,0 @@
-# File managed by web3-bot. DO NOT EDIT.
-# See https://github.com/protocol/.github/ for details.
-
-name: Releaser
-on:
-  push:
-    paths: [ 'version.json' ]
-
-jobs:
-  releaser:
-    uses: protocol/.github/.github/workflows/releaser.yml@master

.github/workflows/stale.yml

@@ -1,26 +0,0 @@
-name: Close and mark stale issue
-
-on:
-  schedule:
-  - cron: '0 0 * * *'
-
-jobs:
-  stale:
-
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-
-    steps:
-    - uses: actions/stale@v3
-      with:
-        repo-token: ${{ secrets.GITHUB_TOKEN }}
-        stale-issue-message: 'Oops, seems like we needed more information for this issue, please comment with more details or this issue will be closed in 7 days.'
-        close-issue-message: 'This issue was closed because it is missing author input.'
-        stale-issue-label: 'kind/stale'
-        any-of-labels: 'need/author-input'
-        exempt-issue-labels: 'need/triage,need/community-input,need/maintainer-input,need/maintainers-input,need/analysis,status/blocked,status/in-progress,status/ready,status/deferred,status/inactive'
-        days-before-issue-stale: 6
-        days-before-issue-close: 7
-        enable-statistics: true

.github/workflows/tagpush.yml

@@ -1,12 +0,0 @@
-# File managed by web3-bot. DO NOT EDIT.
-# See https://github.com/protocol/.github/ for details.
-
-name: Tag Push Checker
-on:
-  push:
-    tags:
-      - v*
-
-jobs:
-  releaser:
-    uses: protocol/.github/.github/workflows/tagpush.yml@master

README.md

@@ -59,17 +59,10 @@ fmt.Println("Got CID: ", c)
 #### Creating a CID from scratch
 
 ```go
-
-import (
-  cid "github.com/ipfs/go-cid"
-  mc "github.com/multiformats/go-multicodec"
-  mh "github.com/multiformats/go-multihash"
-)
-
 // Create a cid manually by specifying the 'prefix' parameters
 pref := cid.Prefix{
 	Version: 1,
-	Codec: mc.Raw,
+	Codec: cid.Raw,
 	MhType: mh.SHA2_256,
 	MhLength: -1, // default length
 }

benchmark_test.go

@@ -1,61 +0,0 @@
-package cid_test
-
-import (
-	"math/rand"
-	"testing"
-
-	"github.com/ipfs/go-cid"
-	"github.com/multiformats/go-multihash"
-)
-
-// BenchmarkIdentityCheck benchmarks two ways of checking whether a CIDv1 has multihash.IDENTITY
-// code:
-//  1. Cid.Prefix(), and
-//  2. decoding the Cid.Hash().
-//
-// This benchmark illustrates that using Cid.Prefix is more efficient than multihash.Decode.
-// Users wishing to perform such a check should use Cid.Prefix.
-//
-// Consider that `Cid.Prefix` is already efficient enough and introducing a dedicated API for
-// performing this check will likely result in small gains.
-func BenchmarkIdentityCheck(b *testing.B) {
-	rng := rand.New(rand.NewSource(1413))
-
-	data := make([]byte, rng.Intn(100)+1024)
-	if _, err := rng.Read(data); err != nil {
-		b.Fatal(err)
-	}
-	mh, err := multihash.Sum(data, multihash.IDENTITY, -1)
-	if err != nil {
-		b.Fatal(err)
-	}
-	cv1 := cid.NewCidV1(cid.Raw, mh)
-
-	b.SetBytes(int64(cv1.ByteLen()))
-	b.ReportAllocs()
-	b.ResetTimer()
-
-	b.Run("Prefix", func(b *testing.B) {
-		b.RunParallel(func(pb *testing.PB) {
-			for pb.Next() {
-				if cv1.Prefix().MhType != multihash.IDENTITY {
-					b.Fatal("expected IDENTITY CID")
-				}
-			}
-		})
-	})
-
-	b.Run("MultihashDecode", func(b *testing.B) {
-		b.RunParallel(func(pb *testing.PB) {
-			for pb.Next() {
-				dmh, err := multihash.Decode(cv1.Hash())
-				if err != nil {
-					b.Fatal(err)
-				}
-				if dmh.Code != multihash.IDENTITY {
-					b.Fatal("expected IDENTITY CID")
-				}
-			}
-		})
-	})
-}

cid.go

@@ -22,7 +22,6 @@ package cid
 import (
 	"bytes"
 	"encoding"
-	"encoding/binary"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -47,21 +46,19 @@ var (
 	ErrInvalidEncoding = errors.New("invalid base encoding")
 )
 
-// Consts below are DEPRECATED and left only for legacy reasons:
+// These are multicodec-packed content types. The should match
-// <https://github.com/ipfs/go-cid/pull/137>
+// the codes described in the authoritative document:
-// Modern code should use consts from go-multicodec instead:
+// https://github.com/multiformats/multicodec/blob/master/table.csv
-// <https://github.com/multiformats/go-multicodec>
 const (
-	// common ones
+	Raw = 0x55
-	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
+	DagProtobuf = 0x70
-	GitRaw                = 0x78
+	DagCBOR     = 0x71
-	DagJOSE               = 0x85 // https://ipld.io/specs/codecs/dag-jose/spec/
+	Libp2pKey   = 0x72
+
+	GitRaw = 0x78
+
+	DagJOSE               = 0x85
 	EthBlock              = 0x90
 	EthBlockList          = 0x91
 	EthTxTrie             = 0x92
@@ -83,6 +80,64 @@ const (
 	FilCommitmentSealed   = 0xf102
 )
 
+// Codecs maps the name of a codec to its type
+var Codecs = map[string]uint64{
+	"v0":                      DagProtobuf,
+	"raw":                     Raw,
+	"protobuf":                DagProtobuf,
+	"cbor":                    DagCBOR,
+	"libp2p-key":              Libp2pKey,
+	"git-raw":                 GitRaw,
+	"eth-block":               EthBlock,
+	"eth-block-list":          EthBlockList,
+	"eth-tx-trie":             EthTxTrie,
+	"eth-tx":                  EthTx,
+	"eth-tx-receipt-trie":     EthTxReceiptTrie,
+	"eth-tx-receipt":          EthTxReceipt,
+	"eth-state-trie":          EthStateTrie,
+	"eth-account-snapshot":    EthAccountSnapshot,
+	"eth-storage-trie":        EthStorageTrie,
+	"bitcoin-block":           BitcoinBlock,
+	"bitcoin-tx":              BitcoinTx,
+	"zcash-block":             ZcashBlock,
+	"zcash-tx":                ZcashTx,
+	"decred-block":            DecredBlock,
+	"decred-tx":               DecredTx,
+	"dash-block":              DashBlock,
+	"dash-tx":                 DashTx,
+	"fil-commitment-unsealed": FilCommitmentUnsealed,
+	"fil-commitment-sealed":   FilCommitmentSealed,
+	"dag-jose":                DagJOSE,
+}
+
+// CodecToStr maps the numeric codec to its name
+var CodecToStr = map[uint64]string{
+	Raw:                   "raw",
+	DagProtobuf:           "protobuf",
+	DagCBOR:               "cbor",
+	GitRaw:                "git-raw",
+	EthBlock:              "eth-block",
+	EthBlockList:          "eth-block-list",
+	EthTxTrie:             "eth-tx-trie",
+	EthTx:                 "eth-tx",
+	EthTxReceiptTrie:      "eth-tx-receipt-trie",
+	EthTxReceipt:          "eth-tx-receipt",
+	EthStateTrie:          "eth-state-trie",
+	EthAccountSnapshot:    "eth-account-snapshot",
+	EthStorageTrie:        "eth-storage-trie",
+	BitcoinBlock:          "bitcoin-block",
+	BitcoinTx:             "bitcoin-tx",
+	ZcashBlock:            "zcash-block",
+	ZcashTx:               "zcash-tx",
+	DecredBlock:           "decred-block",
+	DecredTx:              "decred-tx",
+	DashBlock:             "dash-block",
+	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
 // error on failure.
 func tryNewCidV0(mhash mh.Multihash) (Cid, error) {
@@ -118,24 +173,16 @@ func NewCidV0(mhash mh.Multihash) Cid {
 // Panics if the multihash is invalid.
 func NewCidV1(codecType uint64, mhash mh.Multihash) Cid {
 	hashlen := len(mhash)
-
+	// two 8 bytes (max) numbers plus hash
-	// Two 8 bytes (max) numbers plus hash.
+	buf := make([]byte, 1+varint.UvarintSize(codecType)+hashlen)
-	// We use strings.Builder to only allocate once.
+	n := varint.PutUvarint(buf, 1)
-	var b strings.Builder
+	n += varint.PutUvarint(buf[n:], codecType)
-	b.Grow(1 + varint.UvarintSize(codecType) + hashlen)
+	cn := copy(buf[n:], mhash)
-
-	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()}
+	return Cid{string(buf[:n+hashlen])}
 }
 
 var (
@@ -181,15 +228,6 @@ func Parse(v interface{}) (Cid, error) {
 	}
 }
 
-// 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:
 //
@@ -378,13 +416,7 @@ func (c Cid) Hash() mh.Multihash {
 // 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)
 }
 
@@ -761,7 +793,7 @@ func CidFromReader(r io.Reader) (int, Cid, error) {
 	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))...)
+		br.dst = append(br.dst, make([]byte, cidLength-cap(br.dst))...)
 	} else {
 		// The multihash digest fits inside our buffer,
 		// so just extend its capacity.

cid_fuzz.go

@@ -1,4 +1,3 @@
-//go:build gofuzz
 // +build gofuzz
 
 package cid

cid_test.go

@@ -15,6 +15,37 @@ import (
 	mh "github.com/multiformats/go-multihash"
 )
 
+// Copying the "silly test" idea from
+// https://github.com/multiformats/go-multihash/blob/7aa9f26a231c6f34f4e9fad52bf580fd36627285/multihash_test.go#L13
+// Makes it so changing the table accidentally has to happen twice.
+var tCodecs = map[uint64]string{
+	Raw:                   "raw",
+	DagProtobuf:           "protobuf",
+	DagCBOR:               "cbor",
+	Libp2pKey:             "libp2p-key",
+	GitRaw:                "git-raw",
+	EthBlock:              "eth-block",
+	EthBlockList:          "eth-block-list",
+	EthTxTrie:             "eth-tx-trie",
+	EthTx:                 "eth-tx",
+	EthTxReceiptTrie:      "eth-tx-receipt-trie",
+	EthTxReceipt:          "eth-tx-receipt",
+	EthStateTrie:          "eth-state-trie",
+	EthAccountSnapshot:    "eth-account-snapshot",
+	EthStorageTrie:        "eth-storage-trie",
+	BitcoinBlock:          "bitcoin-block",
+	BitcoinTx:             "bitcoin-tx",
+	ZcashBlock:            "zcash-block",
+	ZcashTx:               "zcash-tx",
+	DecredBlock:           "decred-block",
+	DecredTx:              "decred-tx",
+	DashBlock:             "dash-block",
+	DashTx:                "dash-tx",
+	FilCommitmentUnsealed: "fil-commitment-unsealed",
+	FilCommitmentSealed:   "fil-commitment-sealed",
+	DagJOSE:               "dag-jose",
+}
+
 func assertEqual(t *testing.T, a, b Cid) {
 	if a.Type() != b.Type() {
 		t.Fatal("mismatch on type")
@@ -29,6 +60,26 @@ func assertEqual(t *testing.T, a, b Cid) {
 	}
 }
 
+func TestTable(t *testing.T) {
+	if len(tCodecs) != len(Codecs)-1 {
+		t.Errorf("Item count mismatch in the Table of Codec. Should be %d, got %d", len(tCodecs)+1, len(Codecs))
+	}
+
+	for k, v := range tCodecs {
+		if Codecs[v] != k {
+			t.Errorf("Table mismatch: 0x%x %s", k, v)
+		}
+	}
+}
+
+// The table returns cid.DagProtobuf for "v0"
+// so we test it apart
+func TestTableForV0(t *testing.T) {
+	if Codecs["v0"] != DagProtobuf {
+		t.Error("Table mismatch: Codecs[\"v0\"] should resolve to DagProtobuf (0x70)")
+	}
+}
+
 func TestPrefixSum(t *testing.T) {
 	// Test creating CIDs both manually and with Prefix.
 	// Tests: https://github.com/ipfs/go-cid/issues/83
@@ -616,7 +667,6 @@ func TestReadCidsFromBuffer(t *testing.T) {
 		"k2cwueckqkibutvhkr4p2ln2pjcaxaakpd9db0e7j7ax1lxhhxy3ekpv",
 		"Qmf5Qzp6nGBku7CEn2UQx4mgN8TW69YUok36DrGa6NN893",
 		"zb2rhZi1JR4eNc2jBGaRYJKYM8JEB4ovenym8L1CmFsRAytkz",
-		"bafkqarjpmzuwyzltorxxezjpkvcfgqkfjfbfcvslivje2vchkzdu6rckjjcfgtkolaze6mssjqzeyn2ekrcfatkjku2vowseky3fswkfkm2deqkrju3e2",
 	}
 
 	var cids []Cid

go.mod

@@ -4,17 +4,7 @@ require (
 	github.com/multiformats/go-multibase v0.0.3
 	github.com/multiformats/go-multihash v0.0.15
 	github.com/multiformats/go-varint v0.0.6
-)
-
-require (
-	github.com/klauspost/cpuid/v2 v2.0.4 // indirect
-	github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1 // indirect
-	github.com/minio/sha256-simd v1.0.0 // indirect
-	github.com/mr-tron/base58 v1.2.0 // indirect
-	github.com/multiformats/go-base32 v0.0.3 // indirect
-	github.com/multiformats/go-base36 v0.1.0 // indirect
 	golang.org/x/crypto v0.0.0-20210506145944-38f3c27a63bf // indirect
-	golang.org/x/sys v0.0.0-20210309074719-68d13333faf2 // indirect
 )
 
-go 1.17
+go 1.15

version.json

@@ -1,3 +0,0 @@
-{
-  "version": "v0.3.0"
-}