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 list and filter commands #227

Merged
merged 4 commits into from
Sep 10, 2021
Merged
Show file tree
Hide file tree
Changes from all 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
26 changes: 22 additions & 4 deletions v2/cmd/car/car.go
Original file line number Diff line number Diff line change
Expand Up @@ -28,10 +28,28 @@ func main() {
},
},
{
Name: "split",
Aliases: []string{"s"},
Usage: "Split an index to a detached file",
Action: SplitCar,
Name: "detach-index",
Usage: "Detach an index to a detached file",
Action: DetachCar,
},
{
Name: "list",
Aliases: []string{"l"},
Usage: "List the CIDs in a car",
Action: ListCar,
},
{
Name: "filter",
Aliases: []string{"f"},
Usage: "Filter the CIDs in a car",
Action: FilterCar,
Flags: []cli.Flag{
&cli.StringFlag{
Name: "cid-file",
Usage: "A file to read CIDs from",
TakesFile: true,
},
},
},
},
}
Expand Down
4 changes: 2 additions & 2 deletions v2/cmd/car/split.go → v2/cmd/car/detach.go
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,8 @@ import (
"github.com/urfave/cli/v2"
)

// SplitCar is a command to output the index part of a car.
func SplitCar(c *cli.Context) error {
// DetachCar is a command to output the index part of a car.
func DetachCar(c *cli.Context) error {
r, err := carv2.OpenReader(c.Args().Get(0))
if err != nil {
return err
Expand Down
98 changes: 98 additions & 0 deletions v2/cmd/car/filter.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,98 @@
package main

import (
"bufio"
"fmt"
"io"
"os"
"strings"

"github.com/ipfs/go-cid"
carv2 "github.com/ipld/go-car/v2"
"github.com/ipld/go-car/v2/blockstore"
icarv1 "github.com/ipld/go-car/v2/internal/carv1"
"github.com/urfave/cli/v2"
)

// FilterCar is a command to select a subset of a car by CID.
func FilterCar(c *cli.Context) error {
r, err := carv2.OpenReader(c.Args().Get(0))
if err != nil {
return err
}
defer r.Close()

if c.Args().Len() < 2 {
return fmt.Errorf("an output filename must be provided")
}
roots, err := r.Roots()
if err != nil {
return err
}
bs, err := blockstore.OpenReadWrite(c.Args().Get(1), roots)
if err != nil {
return err
}

// Get the set of CIDs from stdin.
inStream := os.Stdin
if c.IsSet("cidFile") {
inStream, err = os.Open(c.String("cidFile"))
if err != nil {
return err
}
defer inStream.Close()
}
cidMap, err := parseCIDS(inStream)
if err != nil {
return err
}
fmt.Printf("filtering to %d cids\n", len(cidMap))

rd, err := icarv1.NewCarReader(r.DataReader())
if err != nil {
return err
}

for {
blk, err := rd.Next()
if err != nil {
if err == io.EOF {
break
}
return err
}
if _, ok := cidMap[blk.Cid()]; ok {
if err := bs.Put(blk); err != nil {
return err
}
}
}
return bs.Finalize()
}

func parseCIDS(r io.Reader) (map[cid.Cid]struct{}, error) {
cids := make(map[cid.Cid]struct{})
br := bufio.NewReader(r)
for {
line, _, err := br.ReadLine()
if err != nil {
if err == io.EOF {
return cids, nil
}
return nil, err
}
trimLine := strings.TrimSpace(string(line))
if len(trimLine) == 0 {
continue
}
c, err := cid.Parse(trimLine)
if err != nil {
return nil, err
}
if _, ok := cids[c]; ok {
fmt.Fprintf(os.Stderr, "duplicate cid: %s\n", c)
}
cids[c] = struct{}{}
}
}
53 changes: 53 additions & 0 deletions v2/cmd/car/list.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
package main

import (
"fmt"
"io"
"os"

carv2 "github.com/ipld/go-car/v2"
"github.com/urfave/cli/v2"
)

// ListCar is a command to output the cids in a car.
func ListCar(c *cli.Context) error {
inStream := os.Stdin
var err error
if c.Args().Len() >= 1 {
inStream, err = os.Open(c.Args().First())
if err != nil {
return err
}
defer inStream.Close()
}
rd, err := carv2.NewBlockReader(inStream)
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()

if err != nil {
return err
}

for {
blk, err := rd.Next()
if err != nil {
if err == io.EOF {
break
}
return err
}
fmt.Fprintf(outStream, "%s\n", blk.Cid())
}

return err
}