Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add carve utility for updating the index of a car{v1,v2} file #219

Merged
merged 6 commits into from
Sep 8, 2021
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
158 changes: 158 additions & 0 deletions v2/cmd/car/car.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
package main

import (
"bufio"
"fmt"
"io"
"log"
"os"

"github.com/ipfs/go-cid"
carv1 "github.com/ipld/go-car"
carv2 "github.com/ipld/go-car/v2"
"github.com/ipld/go-car/v2/index"
"github.com/multiformats/go-multicodec"
"github.com/multiformats/go-varint"
"github.com/urfave/cli/v2"
)

func main() {
app := &cli.App{
Name: "car",
Usage: "Utility for working with car files",
Flags: []cli.Flag{
&cli.StringFlag{
Name: "codec",
Aliases: []string{"c"},
Usage: "The type of index to write",
Value: "CarMultihashIndexSorted",
},
},
Commands: []*cli.Command{
{
Name: "index",
Aliases: []string{"i"},
Usage: "write out the car with an index",
Action: func(c *cli.Context) error {
r, err := carv2.OpenReader(c.Args().Get(0))
if err != nil {
return err
}
defer r.Close()

var idx index.Index
if c.String("codec") != "none" {
var mc multicodec.Code
if err := mc.Set(c.String("codec")); err != nil {
return fmt.Errorf("unknown codec: %s", c.String("codec"))
}
idx, err = index.New(mc)
if err != nil {
return err
}
}

outStream := os.Stdout
if c.Args().Len() >= 2 {
outStream, err = os.Create(c.Args().Get(1))
if err != nil {
return err
}
}
defer outStream.Close()

v1r := r.DataReader()

v2Header := carv2.NewHeader(r.Header.DataSize)
if c.String("codec") == "none" {
v2Header.IndexOffset = 0
if _, err := outStream.Write(carv2.Pragma); err != nil {
return err
}
if _, err := v2Header.WriteTo(outStream); err != nil {
return err
}
if _, err := io.Copy(outStream, v1r); err != nil {
return err
}
return nil
}

if _, err := outStream.Write(carv2.Pragma); err != nil {
return err
}
if _, err := v2Header.WriteTo(outStream); err != nil {
return err
}

// collect records as we go through the v1r
rdr, err := carv1.NewCarReader(v1r)
if err != nil {
return fmt.Errorf("error reading car header: %w", err)
}
if err := carv1.WriteHeader(rdr.Header, outStream); err != nil {
return err
}

records := make([]index.Record, 0)
var sectionOffset int64
if sectionOffset, err = v1r.Seek(0, io.SeekCurrent); err != nil {
return err
}

br := bufio.NewReader(v1r)
for {
// Read the section's length.
sectionLen, err := varint.ReadUvarint(br)
if err != nil {
if err == io.EOF {
break
}
return err
}
if _, err := outStream.Write(varint.ToUvarint(sectionLen)); err != nil {
return err
}

// Null padding; by default it's an error.
// TODO: integrate corresponding ReadOption
if sectionLen == 0 {
// TODO: pad writer to expected length.
break
}

// Read the CID.
cidLen, c, err := cid.CidFromReader(br)
if err != nil {
return err
}
records = append(records, index.Record{Cid: c, Offset: uint64(sectionOffset)})
if _, err := c.WriteBytes(outStream); err != nil {
return err
}

// Seek to the next section by skipping the block.
// The section length includes the CID, so subtract it.
remainingSectionLen := int64(sectionLen) - int64(cidLen)
if _, err := io.CopyN(outStream, br, remainingSectionLen); err != nil {
return err
}
sectionOffset += int64(sectionLen) + int64(varint.UvarintSize(sectionLen))
}

if err := idx.Load(records); err != nil {
return err
}

return index.WriteTo(idx, outStream)
},
},
},
}

err := app.Run(os.Args)
if err != nil {
log.Fatal(err)
os.Exit(1)
}
}
2 changes: 2 additions & 0 deletions v2/go.mod
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,15 @@ require (
github.com/ipfs/go-ipld-cbor v0.0.5
github.com/ipfs/go-ipld-format v0.2.0
github.com/ipfs/go-merkledag v0.3.2
github.com/ipld/go-car v0.3.1
github.com/klauspost/cpuid/v2 v2.0.8 // indirect
github.com/mattn/go-colorable v0.1.8 // indirect
github.com/multiformats/go-multicodec v0.3.1-0.20210902112759-1539a079fd61
github.com/multiformats/go-multihash v0.0.15
github.com/multiformats/go-varint v0.0.6
github.com/petar/GoLLRB v0.0.0-20210522233825-ae3b015fd3e9
github.com/stretchr/testify v1.7.0
github.com/urfave/cli/v2 v2.3.0
github.com/whyrusleeping/cbor v0.0.0-20171005072247-63513f603b11
golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97 // indirect
golang.org/x/exp v0.0.0-20210615023648-acb5c1269671
Expand Down
28 changes: 25 additions & 3 deletions v2/go.sum
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@ github.com/coreos/go-semver v0.3.0/go.mod h1:nnelYz7RCh+5ahJtPPxZlU+153eP4D4r3Ee
github.com/coreos/go-systemd v0.0.0-20180511133405-39ca1b05acc7/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
github.com/coreos/go-systemd v0.0.0-20190321100706-95778dfbb74e/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
github.com/coreos/pkg v0.0.0-20160727233714-3ac0863d7acf/go.mod h1:E3G3o1h8I7cfcXa63jLwjI0eiQQMgzzUDFVpN/nH/eA=
github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d h1:U+s90UTSYgptZMwQh2aRr3LuazLJIa+Pg3Kc1ylSYVY=
github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
github.com/creack/pty v1.1.7/go.mod h1:lj5s0c3V2DBrqTV7llrYr5NG6My20zk30Fl46Y7DoTY=
github.com/cskr/pubsub v1.0.2 h1:vlOzMhl6PFn60gRlTQQsIfVwaPB/B/8MziK8FhEPt/0=
Expand All @@ -76,6 +77,8 @@ github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7
github.com/fatih/color v1.7.0/go.mod h1:Zm6kSWBoL9eyXnKyktHP6abPY2pDugNf5KwzbycvMj4=
github.com/franela/goblin v0.0.0-20200105215937-c9ffbefa60db/go.mod h1:7dvUGVsVBjqR7JHJk0brhHOZYGmfBYOrK0ZhYMEtBr4=
github.com/franela/goreq v0.0.0-20171204163338-bcd34c9993f8/go.mod h1:ZhphrRTfi2rbfLwlschooIH4+wKKDR4Pdxhh+TRoA20=
github.com/frankban/quicktest v1.11.3 h1:8sXhOn0uLys67V8EsXLc6eszDs8VXWxL3iRvebPhedY=
github.com/frankban/quicktest v1.11.3/go.mod h1:wRf/ReqHper53s+kmmSZizM8NamnL3IM0I9ntUbOk+k=
github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
github.com/go-check/check v0.0.0-20180628173108-788fd7840127/go.mod h1:9ES+weclKsC9YodN5RgxqK/VD9HM9JsCSh7rNhMZE98=
Expand Down Expand Up @@ -110,6 +113,8 @@ github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5a
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.4/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU=
github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
Expand Down Expand Up @@ -171,6 +176,7 @@ github.com/ipfs/go-blockservice v0.1.0/go.mod h1:hzmMScl1kXHg3M2BjTymbVPjv627N7s
github.com/ipfs/go-cid v0.0.1/go.mod h1:GHWU/WuQdMPmIosc4Yn1bcCT7dSeX4lBafM7iqUPQvM=
github.com/ipfs/go-cid v0.0.2/go.mod h1:GHWU/WuQdMPmIosc4Yn1bcCT7dSeX4lBafM7iqUPQvM=
github.com/ipfs/go-cid v0.0.3/go.mod h1:GHWU/WuQdMPmIosc4Yn1bcCT7dSeX4lBafM7iqUPQvM=
github.com/ipfs/go-cid v0.0.4/go.mod h1:4LLaPOQwmk5z9LBgQnpkivrx8BJjUyGwTXCd5Xfj6+M=
github.com/ipfs/go-cid v0.0.5/go.mod h1:plgt+Y5MnOey4vO4UlUazGqdbEXuFYitED67FexhXog=
github.com/ipfs/go-cid v0.0.7/go.mod h1:6Ux9z5e+HpkQdckYoX1PG/6xqKspzlEIR5SDmgqgC/I=
github.com/ipfs/go-cid v0.0.8-0.20210716091050-de6c03deae1c h1:uVMZWk8sJN1l/47TtXRXDz0M9/6v0yw7neDn5WfeLwg=
Expand Down Expand Up @@ -225,6 +231,12 @@ github.com/ipfs/go-peertaskqueue v0.1.0 h1:bpRbgv76eT4avutNPDFZuCPOQus6qTgurEYxf
github.com/ipfs/go-peertaskqueue v0.1.0/go.mod h1:Jmk3IyCcfl1W3jTW3YpghSwSEC6IJ3Vzz/jUmWw8Z0U=
github.com/ipfs/go-verifcid v0.0.1 h1:m2HI7zIuR5TFyQ1b79Da5N9dnnCP1vcu2QqawmWlK2E=
github.com/ipfs/go-verifcid v0.0.1/go.mod h1:5Hrva5KBeIog4A+UpqlaIU+DEstipcJYQQZc0g37pY0=
github.com/ipld/go-car v0.3.1 h1:WT+3cdmXlvmWOlGxk9webhj4auGO5QvgqC2vCCkFRXs=
github.com/ipld/go-car v0.3.1/go.mod h1:dPkEWeAK8KaVvH5TahaCs6Mncpd4lDMpkbs0/SPzuVs=
github.com/ipld/go-codec-dagpb v1.2.0 h1:2umV7ud8HBMkRuJgd8gXw95cLhwmcYrihS3cQEy9zpI=
github.com/ipld/go-codec-dagpb v1.2.0/go.mod h1:6nBN7X7h8EOsEejZGqC7tej5drsdBAXbMHyBT+Fne5s=
github.com/ipld/go-ipld-prime v0.9.0 h1:N2OjJMb+fhyFPwPnVvJcWU/NsumP8etal+d2v3G4eww=
github.com/ipld/go-ipld-prime v0.9.0/go.mod h1:KvBLMr4PX1gWptgkzRjVZCrLmSGcZCb/jioOQwCqZN8=
github.com/jackpal/gateway v1.0.5 h1:qzXWUJfuMdlLMtt0a3Dgt+xkWQiA5itDEITVJtuSwMc=
github.com/jackpal/gateway v1.0.5/go.mod h1:lTpwd4ACLXmpyiCTRtfiNyVnUmqT9RivzCDQetPfnjA=
github.com/jackpal/go-nat-pmp v1.0.1 h1:i0LektDkO1QlrTm/cSuP+PyBCDnYvjPLGl4LdWEMiaA=
Expand Down Expand Up @@ -257,8 +269,9 @@ github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxv
github.com/koron/go-ssdp v0.0.0-20180514024734-4a0ed625a78b h1:wxtKgYHEncAU00muMD06dzLiahtGM1eouRNOzVV7tdQ=
github.com/koron/go-ssdp v0.0.0-20180514024734-4a0ed625a78b/go.mod h1:5Ky9EC2xfoUKUor0Hjgi2BJhCSXJfMOFlmyYrVKGQMk=
github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
Expand Down Expand Up @@ -428,8 +441,10 @@ github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINE
github.com/pkg/profile v1.2.1/go.mod h1:hJw3o1OdXxsrSjjVksARp5W95eeEaEfptyVZyv6JUPA=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/polydawn/refmt v0.0.0-20190221155625-df39d6c2d992 h1:bzMe+2coZJYHnhGgVlcQKuRy4FSny4ds8dLQjw5P1XE=
github.com/polydawn/refmt v0.0.0-20190221155625-df39d6c2d992/go.mod h1:uIp+gprXxxrWSjjklXD+mN4wed/tMfjMMmN/9+JsA9o=
github.com/polydawn/refmt v0.0.0-20190807091052-3d65705ee9f1/go.mod h1:uIp+gprXxxrWSjjklXD+mN4wed/tMfjMMmN/9+JsA9o=
github.com/polydawn/refmt v0.0.0-20201211092308-30ac6d18308e h1:ZOcivgkkFRnjfoTcGsDq3UQYiBmekwLA+qg0OjyB/ls=
github.com/polydawn/refmt v0.0.0-20201211092308-30ac6d18308e/go.mod h1:uIp+gprXxxrWSjjklXD+mN4wed/tMfjMMmN/9+JsA9o=
github.com/posener/complete v1.1.1/go.mod h1:em0nMJCgc9GFtwrmVmEMR/ZL6WyhyjMBndrE9hABlRI=
github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
github.com/prometheus/client_golang v0.9.3-0.20190127221311-3c4408c8b829/go.mod h1:p2iRAGwDERtqlqzRXnrOVns+ignqQo//hLXqYxZYVNs=
Expand All @@ -452,10 +467,12 @@ github.com/rogpeppe/fastuuid v0.0.0-20150106093220-6724a57986af/go.mod h1:XWv6So
github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
github.com/rs/xid v1.2.1/go.mod h1:+uKXf+4Djp6Md1KODXJxgGQPKngRmWyn10oCKFzNHOQ=
github.com/rs/zerolog v1.21.0/go.mod h1:ZPhntP/xmq1nnND05hhpAh2QMhSsA4UN3MGZ6O2J3hM=
github.com/russross/blackfriday/v2 v2.0.1 h1:lPqVAte+HuHNfhJ/0LC98ESWRz8afy9tM/0RK8m9o+Q=
github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/ryanuber/columnize v0.0.0-20160712163229-9b3edd62028f/go.mod h1:sm1tb6uqfes/u+d4ooFouqFdy9/2g9QGwK3SQygK0Ts=
github.com/samuel/go-zookeeper v0.0.0-20190923202752-2cc03de413da/go.mod h1:gi+0XIa01GRL2eRQVjQkKGqKF3SF9vZR/HnPullcV2E=
github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc=
github.com/shurcooL/sanitized_anchor_name v1.0.0 h1:PdmoCO6wvbs+7yrJyMORt4/BmY5IYyJwS/kOiWx8mHo=
github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
Expand Down Expand Up @@ -487,9 +504,13 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
github.com/syndtr/goleveldb v1.0.0/go.mod h1:ZVVdQEZoIme9iO1Ch2Jdy24qqXrMMOU6lpPAyBWyWuQ=
github.com/tmc/grpc-websocket-proxy v0.0.0-20170815181823-89b8d40f7ca8/go.mod h1:ncp9v5uamzpCO7NfCPTXjqaC+bZgJeR0sMTm6dMHP7U=
github.com/urfave/cli v1.20.0/go.mod h1:70zkFmudgCuE/ngEzBv17Jvp/497gISqfk5gWijbERA=
github.com/urfave/cli v1.22.1 h1:+mkCCcOFKPnCmVYVcURKps1Xe+3zP90gSYGNfRkjoIY=
github.com/urfave/cli v1.22.1/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0=
github.com/warpfork/go-wish v0.0.0-20180510122957-5ad1f5abf436 h1:qOpVTI+BrstcjTZLm2Yz/3sOnqkzj3FQoh0g+E5s3Gc=
github.com/urfave/cli/v2 v2.3.0 h1:qph92Y649prgesehzOrQjdWyxFOp/QVM+6imKHad91M=
github.com/urfave/cli/v2 v2.3.0/go.mod h1:LJmUH05zAU44vOAcrfzZQKsZbVcdbOG8rtL3/XcUArI=
github.com/warpfork/go-wish v0.0.0-20180510122957-5ad1f5abf436/go.mod h1:x6AKhvSSexNrVSrViXSHUEbICjmGXhtgABaHIySUSGw=
github.com/warpfork/go-wish v0.0.0-20200122115046-b9ea61034e4a h1:G++j5e0OC488te356JvdhaM8YS6nMsjLAYF7JxCv07w=
github.com/warpfork/go-wish v0.0.0-20200122115046-b9ea61034e4a/go.mod h1:x6AKhvSSexNrVSrViXSHUEbICjmGXhtgABaHIySUSGw=
github.com/whyrusleeping/cbor v0.0.0-20171005072247-63513f603b11 h1:5HZfQkwe0mIfyDmc1Em5GqlNRzcdtlv4HTNmdpt7XH0=
github.com/whyrusleeping/cbor v0.0.0-20171005072247-63513f603b11/go.mod h1:Wlo/SzPmxVp6vXpGt/zaXhHH0fn4IxgqZc82aKg6bpQ=
github.com/whyrusleeping/cbor-gen v0.0.0-20200123233031-1cdf64d27158 h1:WXhVOwj2USAXB5oMDwRl3piOux2XMV9TANaYxXHdkoE=
Expand Down Expand Up @@ -689,6 +710,7 @@ gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRN
gopkg.in/yaml.v2 v2.0.0-20170812160011-eb3733d160e7/go.mod h1:JAlM8MvJe8wmxCU4Bli9HhUf9+ttbYbLASfIpnQbh74=
gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
honnef.co/go/tools v0.0.0-20180728063816-88497007e858/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
Expand Down