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

[API ] Add some basic sanity checking when creating a dataset #1111

Merged
merged 2 commits into from
Nov 12, 2024
Merged

[API ] Add some basic sanity checking when creating a dataset #1111

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
903cbfe
Add some basic sanity checking when creating a dataset
jbygdell Nov 1, 2024
268133d
Update Readme
jbygdell Nov 1, 2024
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
56 changes: 53 additions & 3 deletions sda/cmd/api/api.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,12 @@ import (
log "github.com/sirupsen/logrus"
)

type dataset struct {
AccessionIDs []string `json:"accession_ids"`
DatasetID string `json:"dataset_id"`
User string `json:"user"`
}

var (
Conf *config.Config
err error
Expand Down Expand Up @@ -313,7 +319,7 @@ func setAccession(c *gin.Context) {
}

func createDataset(c *gin.Context) {
var dataset schema.DatasetMapping
var dataset dataset
if err := c.BindJSON(&dataset); err != nil {
c.AbortWithStatusJSON(
http.StatusBadRequest,
Expand All @@ -326,8 +332,52 @@ func createDataset(c *gin.Context) {
return
}

dataset.Type = "mapping"
marshaledMsg, _ := json.Marshal(&dataset)
if len(dataset.AccessionIDs) == 0 {
c.AbortWithStatusJSON(http.StatusBadRequest, "at least one accessionID is reqired")

return
}

for _, stableID := range dataset.AccessionIDs {
inboxPath, err := Conf.API.DB.GetInboxPath(stableID)
if err != nil {
switch {
case err.Error() == "sql: no rows in result set":
log.Debugln(err.Error())
c.AbortWithStatusJSON(http.StatusBadRequest, fmt.Sprintf("accession ID not found: %s", stableID))

return
default:
log.Debugln(err.Error())
c.AbortWithStatusJSON(http.StatusInternalServerError, err.Error())

return
}
}

_, err = Conf.API.DB.GetCorrID(dataset.User, inboxPath)
if err != nil {
switch {
case err.Error() == "sql: no rows in result set":
log.Debugln(err.Error())
c.AbortWithStatusJSON(http.StatusBadRequest, "accession ID owned by other user")

return
default:
log.Debugln(err.Error())
c.AbortWithStatusJSON(http.StatusInternalServerError, err.Error())

return
}
}
}

mapping := schema.DatasetMapping{
Type: "mapping",
AccessionIDs: dataset.AccessionIDs,
DatasetID: dataset.DatasetID,
}
marshaledMsg, _ := json.Marshal(&mapping)
if err := schema.ValidateJSON(fmt.Sprintf("%s/dataset-mapping.json", Conf.Broker.SchemasPath), marshaledMsg); err != nil {
log.Debugln(err.Error())
c.AbortWithStatusJSON(http.StatusBadRequest, err.Error())
Expand Down
2 changes: 1 addition & 1 deletion sda/cmd/api/api.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ Admin endpoints are only available to a set of whitelisted users specified in th
```

- `/dataset/create`
- accepts `POST` requests with JSON data with the format: `{"accession_ids": ["<FILE_ACCESSION_01>", "<FILE_ACCESSION_02>"], "dataset_id": "<DATASET_01>"}`
- accepts `POST` requests with JSON data with the format: `{"accession_ids": ["<FILE_ACCESSION_01>", "<FILE_ACCESSION_02>"], "dataset_id": "<DATASET_01>", "user": "<SUBMISSION_USER>"}`
- creates a dataset from the list of accession IDs and the dataset ID.

- Error codes
Expand Down
163 changes: 153 additions & 10 deletions sda/cmd/api/api_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -953,11 +953,7 @@ func (suite *TestSuite) TestCreateDataset() {
Conf.API.Admins = []string{"dummy"}
Conf.Broker.SchemasPath = "../../schemas/isolated"

type dataset struct {
AccessionIDs []string `json:"accession_ids"`
DatasetID string `json:"dataset_id"`
}
accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11", "API:accession-id-12", "API:accession-id-13"}, DatasetID: "API:dataset-01"})
accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11"}, DatasetID: "API:dataset-01", User: "dummy"})
// Mock request and response holders
w := httptest.NewRecorder()
r := httptest.NewRequest(http.MethodPost, "/dataset/create", bytes.NewBuffer(accessionMsg))
Expand Down Expand Up @@ -989,16 +985,160 @@ func (suite *TestSuite) TestCreateDataset() {
}

func (suite *TestSuite) TestCreateDataset_BadFormat() {
user := "dummy"
filePath := "/inbox/dummy/file12.c4gh"

fileID, err := Conf.API.DB.RegisterFile(filePath, user)
assert.NoError(suite.T(), err, "failed to register file in database")
err = Conf.API.DB.UpdateFileEventLog(fileID, "uploaded", fileID, user, "{}", "{}")
assert.NoError(suite.T(), err, "failed to update satus of file in database")

encSha := sha256.New()
_, err = encSha.Write([]byte("Checksum"))
assert.NoError(suite.T(), err)

decSha := sha256.New()
_, err = decSha.Write([]byte("DecryptedChecksum"))
assert.NoError(suite.T(), err)

fileInfo := database.FileInfo{
Checksum: fmt.Sprintf("%x", encSha.Sum(nil)),
Size: 1000,
Path: filePath,
DecryptedChecksum: fmt.Sprintf("%x", decSha.Sum(nil)),
DecryptedSize: 948,
}
err = Conf.API.DB.SetArchived(fileInfo, fileID, fileID)
assert.NoError(suite.T(), err, "failed to mark file as Archived")

err = Conf.API.DB.SetVerified(fileInfo, fileID, fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

err = Conf.API.DB.SetAccessionID("API:accession-id-11", fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

err = Conf.API.DB.SetAccessionID("API:accession-id-11", fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

err = Conf.API.DB.UpdateFileEventLog(fileID, "ready", fileID, "finalize", "{}", "{}")
assert.NoError(suite.T(), err, "got (%v) when marking file as ready", err)

gin.SetMode(gin.ReleaseMode)
assert.NoError(suite.T(), setupJwtAuth())
Conf.API.Admins = []string{"dummy"}
Conf.Broker.SchemasPath = "../../schemas/federated"

type dataset struct {
AccessionIDs []string `json:"accession_ids"`
DatasetID string `json:"dataset_id"`
accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11"}, DatasetID: "API:dataset-01", User: "dummy"})
// Mock request and response holders
w := httptest.NewRecorder()
r := httptest.NewRequest(http.MethodPost, "/dataset/create", bytes.NewBuffer(accessionMsg))
r.Header.Add("Authorization", "Bearer "+suite.Token)

_, router := gin.CreateTestContext(w)
router.POST("/dataset/create", isAdmin(), createDataset)

router.ServeHTTP(w, r)
response := w.Result()
body, err := io.ReadAll(response.Body)
assert.NoError(suite.T(), err)
response.Body.Close()

assert.Equal(suite.T(), http.StatusBadRequest, response.StatusCode)
assert.Contains(suite.T(), string(body), "does not match pattern")
}

func (suite *TestSuite) TestCreateDataset_MissingAccessionIDs() {
gin.SetMode(gin.ReleaseMode)
assert.NoError(suite.T(), setupJwtAuth())
Conf.API.Admins = []string{"dummy"}
Conf.Broker.SchemasPath = "../../schemas/isolated"

accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{}, DatasetID: "failure", User: "dummy"})
// Mock request and response holders
w := httptest.NewRecorder()
r := httptest.NewRequest(http.MethodPost, "/dataset/create", bytes.NewBuffer(accessionMsg))
r.Header.Add("Authorization", "Bearer "+suite.Token)

_, router := gin.CreateTestContext(w)
router.POST("/dataset/create", isAdmin(), createDataset)

router.ServeHTTP(w, r)
response := w.Result()
body, err := io.ReadAll(response.Body)
assert.NoError(suite.T(), err)
response.Body.Close()

assert.Equal(suite.T(), http.StatusBadRequest, response.StatusCode)
assert.Contains(suite.T(), string(body), "at least one accessionID is reqired")
}

func (suite *TestSuite) TestCreateDataset_WrongIDs() {
gin.SetMode(gin.ReleaseMode)
assert.NoError(suite.T(), setupJwtAuth())
Conf.API.Admins = []string{"dummy"}
Conf.Broker.SchemasPath = "../../schemas/isolated"

accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11"}, DatasetID: "API:dataset-01", User: "dummy"})
// Mock request and response holders
w := httptest.NewRecorder()
r := httptest.NewRequest(http.MethodPost, "/dataset/create", bytes.NewBuffer(accessionMsg))
r.Header.Add("Authorization", "Bearer "+suite.Token)

_, router := gin.CreateTestContext(w)
router.POST("/dataset/create", isAdmin(), createDataset)

router.ServeHTTP(w, r)
response := w.Result()
body, err := io.ReadAll(response.Body)
assert.NoError(suite.T(), err)
response.Body.Close()

assert.Equal(suite.T(), http.StatusBadRequest, response.StatusCode)
assert.Contains(suite.T(), string(body), "accession ID not found: ")
}

func (suite *TestSuite) TestCreateDataset_WrongUser() {
user := "dummy"
filePath := "/inbox/dummy/file12.c4gh"

fileID, err := Conf.API.DB.RegisterFile(filePath, user)
assert.NoError(suite.T(), err, "failed to register file in database")
err = Conf.API.DB.UpdateFileEventLog(fileID, "uploaded", fileID, user, "{}", "{}")
assert.NoError(suite.T(), err, "failed to update satus of file in database")

encSha := sha256.New()
_, err = encSha.Write([]byte("Checksum"))
assert.NoError(suite.T(), err)

decSha := sha256.New()
_, err = decSha.Write([]byte("DecryptedChecksum"))
assert.NoError(suite.T(), err)

fileInfo := database.FileInfo{
Checksum: fmt.Sprintf("%x", encSha.Sum(nil)),
Size: 1000,
Path: filePath,
DecryptedChecksum: fmt.Sprintf("%x", decSha.Sum(nil)),
DecryptedSize: 948,
}
accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11", "API:accession-id-12", "API:accession-id-13"}, DatasetID: "API:dataset-01"})
err = Conf.API.DB.SetArchived(fileInfo, fileID, fileID)
assert.NoError(suite.T(), err, "failed to mark file as Archived")

err = Conf.API.DB.SetVerified(fileInfo, fileID, fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

err = Conf.API.DB.SetAccessionID("API:accession-id-11", fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

err = Conf.API.DB.SetAccessionID("API:accession-id-11", fileID)
assert.NoError(suite.T(), err, "got (%v) when marking file as verified", err)

gin.SetMode(gin.ReleaseMode)
assert.NoError(suite.T(), setupJwtAuth())
Conf.API.Admins = []string{"dummy"}
Conf.Broker.SchemasPath = "../../schemas/isolated"

accessionMsg, _ := json.Marshal(dataset{AccessionIDs: []string{"API:accession-id-11"}, DatasetID: "API:dataset-01", User: "tester"})
// Mock request and response holders
w := httptest.NewRecorder()
r := httptest.NewRequest(http.MethodPost, "/dataset/create", bytes.NewBuffer(accessionMsg))
Expand All @@ -1009,9 +1149,12 @@ func (suite *TestSuite) TestCreateDataset_BadFormat() {

router.ServeHTTP(w, r)
response := w.Result()
defer response.Body.Close()
body, err := io.ReadAll(response.Body)
assert.NoError(suite.T(), err)
response.Body.Close()

assert.Equal(suite.T(), http.StatusBadRequest, response.StatusCode)
assert.Contains(suite.T(), string(body), "accession ID owned by other user")
}

func (suite *TestSuite) TestReleaseDataset() {
Expand Down
Loading