Compare commits

..

1 Commits

Author SHA1 Message Date
Daniel Martí
41f2377d96 implement CidFromReader
And reuse a CidFromBytes test for it, which includes both CIDv0 and
CIDv1 cases as inputs.

Fixes #126.
2021-07-02 18:35:02 +01:00
19 changed files with 304 additions and 379 deletions

View File

@@ -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
with:
job: '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

View File

@@ -8,28 +8,17 @@ jobs:
unit:
runs-on: ubuntu-latest
name: All
env:
RUNGOGENERATE: false
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v2
with:
submodules: recursive
- uses: actions/setup-go@v3
- uses: actions/setup-go@v2
with:
go-version: "1.19.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
go-version: "1.16.x"
- name: Install staticcheck
run: go install honnef.co/go/tools/cmd/staticcheck@376210a89477dedbe6fdc4484b233998650d7b3c # 2022.1.3 (v0.3.3)
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

View File

@@ -10,59 +10,38 @@ jobs:
fail-fast: false
matrix:
os: [ "ubuntu", "windows", "macos" ]
go: [ "1.18.x", "1.19.x" ]
env:
COVERAGES: ""
runs-on: ${{ format('{0}-latest', matrix.os) }}
name: ${{ matrix.os }} (go ${{ matrix.go }})
go: [ "1.15.x", "1.16.x" ]
runs-on: ${{ matrix.os }}-latest
name: ${{ matrix.os}} (go ${{ matrix.go }})
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v2
with:
submodules: recursive
- uses: actions/setup-go@v3
- uses: actions/setup-go@v2
with:
go-version: ${{ matrix.go }}
- name: Go information
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.
# 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 -shuffle=on -coverprofile=module-coverage.txt -coverpkg=./... ./...
run: go test -v -coverprofile coverage.txt ./...
- name: Run tests (32 bit)
if: ${{ matrix.os != 'macos' }} # can't run 32 bit tests on OSX.
uses: protocol/multiple-go-modules@v1.2
uses: protocol/multiple-go-modules@v1.0
env:
GOARCH: 386
with:
run: |
export "PATH=${{ env.PATH_386 }}:$PATH"
go test -v -shuffle=on ./...
run: go test -v ./...
- name: Run tests with race detector
if: ${{ matrix.os == 'ubuntu' }} # speed things up. Windows and OSX VMs are slow
uses: protocol/multiple-go-modules@v1.2
uses: protocol/multiple-go-modules@v1.0
with:
run: go test -v -race ./...
- name: Collect coverage files
shell: bash
run: echo "COVERAGES=$(find . -type f -name 'module-coverage.txt' | tr -s '\n' ',' | sed 's/,$//')" >> $GITHUB_ENV
- name: Upload coverage to Codecov
uses: codecov/codecov-action@81cd2dc8148241f03f5839d295e000b8f761e378 # v3.1.0
uses: codecov/codecov-action@a1ed4b322b4b38cb846afb5a0ebfa17086917d27 # v1.5.0
with:
files: '${{ env.COVERAGES }}'
file: coverage.txt
env_vars: OS=${{ matrix.os }}, GO=${{ matrix.go }}

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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
}

View File

@@ -39,8 +39,7 @@ type Cid interface {
// and the Multihash length. It does not contains
// any actual content information.
// NOTE: The use -1 in MhLength to mean default length is deprecated,
//
// use the V0Builder or V1Builder structures instead
// use the V0Builder or V1Builder structures instead
type Prefix struct {
Version uint64
Codec uint64

View File

@@ -12,14 +12,14 @@ import (
//
// Sample results on linux amd64 go1.11beta:
//
// BenchmarkCidMap_CidStr-8 100000 16317 ns/op
// BenchmarkCidMap_CidIface-8 100000 20516 ns/op
// BenchmarkCidMap_CidStr-8 100000 16317 ns/op
// BenchmarkCidMap_CidIface-8 100000 20516 ns/op
//
// With benchmem on:
//
// BenchmarkCidMap_CidStr-8 100000 15579 ns/op 11223 B/op 207 allocs/op
// BenchmarkCidMap_CidIface-8 100000 19500 ns/op 12824 B/op 307 allocs/op
// BenchmarkCidMap_StrPlusHax-8 200000 10451 ns/op 7589 B/op 202 allocs/op
// BenchmarkCidMap_CidStr-8 100000 15579 ns/op 11223 B/op 207 allocs/op
// BenchmarkCidMap_CidIface-8 100000 19500 ns/op 12824 B/op 307 allocs/op
// BenchmarkCidMap_StrPlusHax-8 200000 10451 ns/op 7589 B/op 202 allocs/op
//
// We can see here that the impact of interface boxing is significant:
// it increases the time taken to do the inserts to 133%, largely because
@@ -36,6 +36,7 @@ import (
// re-arranges itself, it involves more or less an O(n) copy of the content
// in addition to the alloc itself). This isn't topical to the question of
// whether or not interfaces are a good idea; just for contextualizing.
//
func BenchmarkCidMap_CidStr(b *testing.B) {
for i := 0; i < b.N; i++ {
mp := map[CidStr]int{}

View File

@@ -114,7 +114,7 @@ func NewCidStr(version uint64, codecType uint64, mhash mh.Multihash) CidStr {
//
// For CidV1, the data buffer is in the form:
//
// <version><codec-type><multihash>
// <version><codec-type><multihash>
//
// CidV0 are also supported. In particular, data buffers starting
// with length 34 bytes, which starts with bytes [18,32...] are considered

View File

@@ -110,7 +110,7 @@ func (c CidStruct) Prefix() Prefix {
//
// For CidV1, the data buffer is in the form:
//
// <version><codec-type><multihash>
// <version><codec-type><multihash>
//
// CidV0 are also supported. In particular, data buffers starting
// with length 34 bytes, which starts with bytes [18,32...] are considered

View File

@@ -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")
}
}
})
})
}

225
cid.go
View File

@@ -10,7 +10,7 @@
//
// A CIDv1 has four parts:
//
// <cidv1> ::= <multibase-prefix><cid-version><multicodec-packed-content-type><multihash-content-address>
// <cidv1> ::= <multibase-prefix><cid-version><multicodec-packed-content-type><multihash-content-address>
//
// As shown above, the CID implementation relies heavily on Multiformats,
// particularly Multibase
@@ -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:
// <https://github.com/ipfs/go-cid/pull/137>
// Modern code should use consts from go-multicodec instead:
// <https://github.com/multiformats/go-multicodec>
// 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
const (
// 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
Raw = 0x55
// other
GitRaw = 0x78
DagJOSE = 0x85 // https://ipld.io/specs/codecs/dag-jose/spec/
DagProtobuf = 0x70
DagCBOR = 0x71
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.
// 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)
// 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)
if cn != hashlen {
panic("copy hash length is inconsistent")
}
return Cid{b.String()}
return Cid{string(buf[:n+hashlen])}
}
var (
@@ -181,19 +228,10 @@ 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:
//
// <multibase-type-code><base-encoded-string>
// <multibase-type-code><base-encoded-string>
//
// The base-encoded string represents a:
//
@@ -249,7 +287,7 @@ func ExtractEncoding(v string) (mbase.Encoding, error) {
// Cast takes a Cid data slice, parses it and returns a Cid.
// For CidV1, the data buffer is in the form:
//
// <version><codec-type><multihash>
// <version><codec-type><multihash>
//
// CidV0 are also supported. In particular, data buffers starting
// with length 34 bytes, which starts with bytes [18,32...] are considered
@@ -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)
}
@@ -465,7 +497,7 @@ func (c *Cid) UnmarshalJSON(b []byte) error {
// MarshalJSON procudes a JSON representation of a Cid, which looks as follows:
//
// { "/": "<cid-string>" }
// { "/": "<cid-string>" }
//
// Note that this formatting comes from the IPLD specification
// (https://github.com/ipld/specs/tree/master/ipld)
@@ -522,8 +554,7 @@ func (c Cid) Prefix() Prefix {
// and the Multihash length. It does not contains
// any actual content information.
// NOTE: The use -1 in MhLength to mean default length is deprecated,
//
// use the V0Builder or V1Builder structures instead
// use the V0Builder or V1Builder structures instead
type Prefix struct {
Version uint64
Codec uint64
@@ -562,7 +593,7 @@ func (p Prefix) Sum(data []byte) (Cid, error) {
// Bytes returns a byte representation of a Prefix. It looks like:
//
// <version><codec><mh-type><mh-length>
// <version><codec><mh-type><mh-length>
func (p Prefix) Bytes() []byte {
size := varint.UvarintSize(p.Version)
size += varint.UvarintSize(p.Codec)
@@ -663,10 +694,19 @@ type bufByteReader struct {
direct io.ByteReader
fallback io.Reader
dst []byte
consumed int
dst []byte
}
func (r *bufByteReader) ReadByte() (byte, error) {
// We still have some of the initial bytes to use.
if r.consumed < len(r.dst) {
b := r.dst[r.consumed]
r.consumed++
return b, nil
}
r.consumed++
// The underlying reader has ReadByte; use it.
if br := r.direct; br != nil {
b, err := br.ReadByte()
@@ -678,8 +718,6 @@ func (r *bufByteReader) ReadByte() (byte, error) {
}
// 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
@@ -699,30 +737,38 @@ 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))
buf := make([]byte, 0, 64)
// We read two bytes, to tell if this is a CIDv0 or a CIDv1.
if n, err := io.ReadFull(r, buf[:2]); err != nil {
return n, Undef, err
}
buf = buf[:2]
// If we have a CIDv0, read the rest of the bytes and cast the buffer.
if buf[0] == mh.SHA2_256 && buf[1] == 32 {
if n, err := io.ReadFull(r, buf[2:34]); err != nil {
return len(buf) + n, Undef, err
}
buf = buf[:34]
h, err := mh.Cast(buf)
if err != nil {
return len(buf), Undef, err
}
return len(buf), Cid{string(h)}, nil
}
// 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.
// Note that we already read two bytes, so bufByteReader uses those first.
// After those two bytes, bufByteReader appends the read bytes to br.dst.
br := toBufByteReader(r, buf[:2])
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)
}
@@ -750,38 +796,29 @@ func CidFromReader(r io.Reader) (int, Cid, error) {
return len(br.dst), Undef, err
}
// Update buf's length.
// We're not reading single bytes beyond this point.
buf = br.dst
br = nil
// Multihash digest; might be too long, so allocate.
// Refuse to make large allocations to prevent OOMs due to bugs.
// TODO: reuse buf if it has enough space
const maxDigestAlloc = 32 << 20 // 32MiB
if mhl > maxDigestAlloc {
return len(br.dst), Undef, fmt.Errorf("refusing to allocate %d bytes for a digest", mhl)
return len(buf), 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-len(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
digest := make([]byte, int(mhl))
if n, err := io.ReadFull(r, digest); err != nil {
return len(buf) + n, Undef, err
}
buf = append(buf, digest...)
// 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:])
_, _, err = mh.MHFromBytes(buf[mhStart:])
if err != nil {
return len(br.dst), Undef, err
return len(buf), Undef, err
}
return len(br.dst), Cid{string(br.dst)}, nil
return len(buf), Cid{string(buf)}, nil
}

View File

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

View File

@@ -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
@@ -671,71 +721,49 @@ func TestReadCidsFromBuffer(t *testing.T) {
}
}
func TestBadCidInput(t *testing.T) {
for _, name := range []string{
"FromBytes",
"FromReader",
} {
t.Run(name, func(t *testing.T) {
usingReader := name == "FromReader"
func TestBadCidFromBytes(t *testing.T) {
l, c, err := CidFromBytes([]byte{mh.SHA2_256, 32, 0x00})
if err == nil {
t.Fatal("expected not-enough-bytes for V0 CidFromBytes")
}
if l != 0 {
t.Fatal("expected length=0 from bad CidFromBytes")
}
if c != Undef {
t.Fatal("expected Undef CID from bad CidFromBytes")
}
fromBytes := CidFromBytes
if usingReader {
fromBytes = func(data []byte) (int, Cid, error) {
return CidFromReader(bytes.NewReader(data))
}
}
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 = CidFromBytes(byts)
if err == nil {
t.Fatal("expected not-enough-bytes for V1 CidFromBytes")
}
if l != 0 {
t.Fatal("expected length=0 from bad CidFromBytes")
}
if c != Undef {
t.Fatal("expected Undef CID from bad CidFromBytes")
}
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")
}
})
copy(byts, c.Bytes())
byts[2] = 0x80 // bad multihash varint
byts[3] = 0x00
l, c, err = CidFromBytes(byts)
if err == nil {
t.Fatal("expected not-enough-bytes for V1 CidFromBytes")
}
if l != 0 {
t.Fatal("expected length=0 from bad CidFromBytes")
}
if c != Undef {
t.Fatal("expected Undef CID from bad CidFromBytes")
}
}

12
go.mod
View File

@@ -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 1.18
go 1.15

5
go.sum
View File

@@ -22,9 +22,14 @@ golang.org/x/crypto v0.0.0-20210220033148-5ea612d1eb83/go.mod h1:jdWPYTVW3xRLrWP
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 v0.0.0-20191026070338-33540a1f6037/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=

View File

@@ -1,3 +0,0 @@
{
"version": "v0.3.2"
}