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.

Sign up for GitHub

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 job source bucket to output path #1101

Merged
merged 3 commits into from
Aug 2, 2022
Merged

Add job source bucket to output path #1101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f929169
Add bucket to output path
stephen-soltesz Jul 30, 2022
1f28a97
Include new output path
stephen-soltesz Jul 30, 2022
5f9891a
Include source bucket in output path
stephen-soltesz Jul 30, 2022
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
2 changes: 1 addition & 1 deletion cmd/etl_worker/etl_worker_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@ func TestLocalRequest(t *testing.T) {
}

// Check the outdir for the successful content of a localwriter.
p := filepath.Join(outdir, "ndt/ndt7/2021/06/17/20210617T003002.410133Z-ndt7-mlab1-foo01-ndt.tgz.jsonl")
p := filepath.Join(outdir, "archive-mlab-testing/ndt/ndt7/2021/06/17/20210617T003002.410133Z-ndt7-mlab1-foo01-ndt.tgz.jsonl")
f, err := os.Open(p)
if err != nil {
t.Fatalf("failed to read file: %v", err)
Expand Down
3 changes: 2 additions & 1 deletion storage/localwriter.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ import (
"log"
"net/http"
"os"
"path"
"path/filepath"

"github.com/m-lab/etl/etl"
Expand Down Expand Up @@ -84,7 +85,7 @@ type LocalFactory struct {

// Get implements factory.SinkFactory for LocalWriters.
func (lf *LocalFactory) Get(ctx context.Context, dp etl.DataPath) (row.Sink, etl.ProcessingError) {
s, err := NewLocalWriter(lf.outputDir, dp.Path+".jsonl")
s, err := NewLocalWriter(lf.outputDir, path.Join(dp.Bucket, dp.Path+".jsonl"))
if err != nil {
return nil, factory.NewError(dp.DataType, "LocalFactory", http.StatusInternalServerError, err)
}
Expand Down
2 changes: 1 addition & 1 deletion storage/localwriter_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,7 +220,7 @@ func TestNewLocalFactory(t *testing.T) {
if tt.wantOpenErr {
// Make directory so open will fail.
err := os.MkdirAll(filepath.Join(tt.outputDir,
"exp/ndt7/2021/06/01/20210601T101003.000001Z-ndt7-mlab4-foo01-exp.tgz.jsonl"), os.ModePerm)
"bucket/exp/ndt7/2021/06/01/20210601T101003.000001Z-ndt7-mlab4-foo01-exp.tgz.jsonl"), os.ModePerm)
testingx.Must(t, err, "failed to mkdir")
}

Expand Down
3 changes: 2 additions & 1 deletion storage/rowwriter.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ import (
"fmt"
"log"
"net/http"
"path"
"time"

gcs "cloud.google.com/go/storage"
Expand Down Expand Up @@ -177,7 +178,7 @@ type SinkFactory struct {

// Get implements factory.SinkFactory
func (sf *SinkFactory) Get(ctx context.Context, dp etl.DataPath) (row.Sink, etl.ProcessingError) {
s, err := NewRowWriter(ctx, sf.client, sf.outputBucket, dp.Path+".json")
s, err := NewRowWriter(ctx, sf.client, sf.outputBucket, path.Join(dp.Bucket, dp.Path+".jsonl"))
if err != nil {
return nil, factory.NewError(dp.DataType, "SinkFactory",
http.StatusInternalServerError, err)
Expand Down
2 changes: 1 addition & 1 deletion worker/worker_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ func TestProcessGKETask(t *testing.T) {
checkCounter(t, c, 478)

// Lookup output from task.
o, err := fs.GetObject("test-bucket", "ndt/ndt5/2019/12/01/20191201T020011.395772Z-ndt5-mlab1-bcn01-ndt.tgz.json")
o, err := fs.GetObject("test-bucket", "test-bucket/ndt/ndt5/2019/12/01/20191201T020011.395772Z-ndt5-mlab1-bcn01-ndt.tgz.jsonl")
if err != nil {
t.Errorf("GetObject() expected nil error, got %v", err)
}
Expand Down