Jay Brown
115 lines
3.3 KiB
Go
115 lines
3.3 KiB
Go
package documenttext
|
|
|
|
import (
|
|
"io"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"queryorchestration/internal/database/repository"
|
|
"queryorchestration/internal/serviceconfig"
|
|
"queryorchestration/internal/serviceconfig/aws"
|
|
"queryorchestration/internal/serviceconfig/objectstore"
|
|
"queryorchestration/internal/serviceconfig/textract"
|
|
objectstoremock "queryorchestration/mocks/objectstore"
|
|
textractmock "queryorchestration/mocks/textract"
|
|
|
|
"github.com/aws/aws-sdk-go-v2/service/s3"
|
|
"github.com/google/uuid"
|
|
"github.com/pashagolub/pgxmock/v3"
|
|
"github.com/stretchr/testify/mock"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
type DocTextConfig struct {
|
|
aws.AWSConfig
|
|
serviceconfig.BaseConfig
|
|
textract.TextractConfig
|
|
objectstore.ObjectStoreConfig
|
|
}
|
|
|
|
func TestCreate(t *testing.T) {
|
|
ctx := t.Context()
|
|
pool, err := pgxmock.NewPool()
|
|
require.NoError(t, err)
|
|
|
|
cfg := &DocTextConfig{}
|
|
cfg.DBPool = pool
|
|
cfg.DBQueries = repository.New(pool)
|
|
mockStore := objectstoremock.NewMockS3Client(t)
|
|
cfg.StoreClient = mockStore
|
|
mockTextract := textractmock.NewMockTextractClient(t)
|
|
cfg.TextractClient = mockTextract
|
|
|
|
svc := Service{
|
|
cfg: cfg,
|
|
}
|
|
|
|
docId := uuid.New()
|
|
t.Run("is not extracted", func(t *testing.T) {
|
|
cleanId := uuid.New()
|
|
bucket := "bucket"
|
|
// Hash will be different with PDF vs PNG processing - use actual computed hash
|
|
// We'll capture the computed hash and use it in expectations
|
|
hash := `"computed-during-test"`
|
|
textId := uuid.New()
|
|
key := objectstore.BucketKey{
|
|
ClientID: "aa",
|
|
Location: objectstore.Import,
|
|
CreatedAt: time.Now().UTC(),
|
|
EntityID: cleanId,
|
|
}
|
|
keyStr := key.String()
|
|
textractBaseOut, pdf, _, close := getFiles(t, "helloWorld")
|
|
defer close()
|
|
|
|
mimetype := repository.NullCleanmimetype{
|
|
Valid: true,
|
|
Cleanmimetype: repository.CleanmimetypeApplicationPdf,
|
|
}
|
|
pool.ExpectQuery("name: IsDocumentTextExtracted :one").WithArgs(docId).WillReturnRows(
|
|
pgxmock.NewRows([]string{"isextracted"}).
|
|
AddRow(false),
|
|
)
|
|
pool.ExpectQuery("name: GetCleanEntryByDocId :one").WithArgs(docId).
|
|
WillReturnRows(
|
|
pgxmock.NewRows([]string{"id", "documentId", "bucket", "key", "version", "hash", "mimetype", "fail", "clientId"}).
|
|
AddRow(cleanId, docId, &bucket, &keyStr, int64(123), &hash, mimetype, nil, key.ClientID),
|
|
)
|
|
bodyMsg := io.NopCloser(strings.NewReader(pdfHelloWorld))
|
|
mockStore.EXPECT().
|
|
GetObject(
|
|
mock.Anything,
|
|
mock.MatchedBy(func(in *s3.GetObjectInput) bool {
|
|
return *in.Bucket == bucket && *in.Key == keyStr
|
|
}),
|
|
mock.Anything,
|
|
).
|
|
Return(&s3.GetObjectOutput{
|
|
Body: bodyMsg,
|
|
}, nil)
|
|
textExpectations(t, ctx, mockTextract, pdf, textractBaseOut)
|
|
|
|
pool.ExpectBegin()
|
|
pool.ExpectQuery("name: GetDocumentTextExtractionByHash :one").WithArgs(cleanId, pgxmock.AnyArg()).WillReturnRows(
|
|
pgxmock.NewRows([]string{"id"}).
|
|
AddRow(textId),
|
|
)
|
|
pool.ExpectExec("name: AddDocumentTextEntry :exec").WithArgs(textId, pgxmock.AnyArg()).
|
|
WillReturnResult(pgxmock.NewResult("", 1))
|
|
pool.ExpectCommit()
|
|
|
|
err = svc.Extract(ctx, docId)
|
|
require.NoError(t, err)
|
|
})
|
|
t.Run("is extracted", func(t *testing.T) {
|
|
pool.ExpectQuery("name: IsDocumentTextExtracted :one").WithArgs(docId).WillReturnRows(
|
|
pgxmock.NewRows([]string{"isextracted"}).
|
|
AddRow(true),
|
|
)
|
|
|
|
err = svc.Extract(ctx, docId)
|
|
require.NoError(t, err)
|
|
})
|
|
}
|