fix: remove invalid multicodec2string mappings (#137)

* refactor: remove Codecs table
* chore: go-cid 0.2.0

Codec table was missing dag-json and it had invalid code for dag-cbor.
It also had invalid string representation of dag-pb -- it was using
'protobuf' which is a totally different code.

This removes invalid mappings entirely.
https://github.com/multiformats/go-multicodec should be used instead.

.github/workflows/automerge.yml

@@ -1,51 +1,11 @@
 # 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
+on: [ pull_request ]
 
 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
+    uses: protocol/.github/.github/workflows/automerge.yml@master
+    with:
+      job: 'automerge'

.github/workflows/go-check.yml

@@ -8,17 +8,28 @@ 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: "1.16.x"
+          go-version: "1.18.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@434f5f3816b358fe468fa83dcba62d794e7fe04b # 2021.1 (v0.2.0)
+        run: go install honnef.co/go/tools/cmd/staticcheck@d7e217c1ff411395475b2971c0824e1e7cc1af98 # 2022.1 (v0.3.0)
       - name: Check that go.mod is tidy
-        uses: protocol/multiple-go-modules@v1.0
+        uses: protocol/multiple-go-modules@v1.2
         with:
           run: |
             go mod tidy
@@ -37,14 +48,26 @@ jobs:
           fi
       - name: go vet
         if: ${{ success() || failure() }} # run this step even if the previous one failed
-        uses: protocol/multiple-go-modules@v1.0
+        uses: protocol/multiple-go-modules@v1.2
         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
+        uses: protocol/multiple-go-modules@v1.2
         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

@@ -10,9 +10,11 @@ jobs:
       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 }})
+        go: [ "1.17.x", "1.18.x" ]
+    env:
+      COVERAGES: ""
+    runs-on: ${{ format('{0}-latest', matrix.os) }}
+    name: ${{ matrix.os }} (go ${{ matrix.go }})
     steps:
       - uses: actions/checkout@v2
         with:
@@ -24,24 +26,43 @@ 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@v1.0
+        uses: protocol/multiple-go-modules@v1.2
         with:
-          run: go test -v -coverprofile coverage.txt ./...
+          # Use -coverpkg=./..., so that we include cross-package coverage.
+          # 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: ${{ matrix.os != 'macos' }} # can't run 32 bit tests on OSX.
-        uses: protocol/multiple-go-modules@v1.0
+        uses: protocol/multiple-go-modules@v1.2
         env:
           GOARCH: 386
         with:
-          run: go test -v ./...
+          run: |
+            export "PATH=${{ env.PATH_386 }}:$PATH"
+            go test -v ./...
       - name: Run tests with race detector
         if: ${{ matrix.os == 'ubuntu' }} # speed things up. Windows and OSX VMs are slow
-        uses: protocol/multiple-go-modules@v1.0
+        uses: protocol/multiple-go-modules@v1.2
         with:
           run: go test -v -race ./...
+      - name: Collect coverage files
+        shell: bash
+        run: echo "COVERAGES=$(find . -type f -name 'module-coverage.txt' | tr -s '\n' ',' | sed 's/,$//')" >> $GITHUB_ENV
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@a1ed4b322b4b38cb846afb5a0ebfa17086917d27 # v1.5.0
+        uses: codecov/codecov-action@f32b3a3741e1053eb607407145bc9619351dc93b # v2.1.0
         with:
-          file: coverage.txt
+          files: '${{ env.COVERAGES }}'
           env_vars: OS=${{ matrix.os }}, GO=${{ matrix.go }}

.github/workflows/release-check.yml

@@ -0,0 +1,11 @@
+# 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

@@ -0,0 +1,11 @@
+# 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/tagpush.yml

@@ -0,0 +1,12 @@
+# 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

@@ -59,10 +59,17 @@ 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: cid.Raw,
+	Codec: mc.Raw,
 	MhType: mh.SHA2_256,
 	MhLength: -1, // default length
 }

benchmark_test.go

@@ -0,0 +1,61 @@
+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

@@ -22,6 +22,7 @@ package cid
 import (
 	"bytes"
 	"encoding"
+	"encoding/binary"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -46,19 +47,21 @@ var (
 	ErrInvalidEncoding = errors.New("invalid base encoding")
 )
 
-// These are multicodec-packed content types. The should match
-// the codes described in the authoritative document:
-// https://github.com/multiformats/multicodec/blob/master/table.csv
+// 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 (
-	Raw = 0x55
+	// 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
 
-	DagProtobuf = 0x70
-	DagCBOR     = 0x71
-	Libp2pKey   = 0x72
-
-	GitRaw = 0x78
-
-	DagJOSE               = 0x85
+	// other
+	GitRaw                = 0x78
+	DagJOSE               = 0x85 // https://ipld.io/specs/codecs/dag-jose/spec/
 	EthBlock              = 0x90
 	EthBlockList          = 0x91
 	EthTxTrie             = 0x92
@@ -80,64 +83,6 @@ 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) {
@@ -173,16 +118,24 @@ 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
-	buf := make([]byte, 1+varint.UvarintSize(codecType)+hashlen)
-	n := varint.PutUvarint(buf, 1)
-	n += varint.PutUvarint(buf[n:], codecType)
-	cn := copy(buf[n:], 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{string(buf[:n+hashlen])}
+	return Cid{b.String()}
 }
 
 var (

cid_fuzz.go

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

cid_test.go

@@ -15,37 +15,6 @@ 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")
@@ -60,26 +29,6 @@ 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

go.mod

@@ -4,7 +4,17 @@ 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
-	golang.org/x/crypto v0.0.0-20210506145944-38f3c27a63bf // indirect
 )
 
-go 1.15
+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

version.json

@@ -0,0 +1,3 @@
+{
+  "version": "v0.2.0"
+}