Merged in feature/textextraction (pull request #110)

Text Extraction

* bases

* go

* splitting

* structure

* movetoasync

* movetoasync

* settinguptrigger

* reorder

* storevent

* standardisepollingvalidation

* unittests

* fixlint

* fixlint

* awscfg

* generatesample

* followthrough

* tests

* clena

* store

* externalidcleanup

* clientid

* local

* baseunittests

* putobjecttests

* tests
This commit is contained in:
Michael McGuinness
2025-04-02 18:50:03 +00:00
parent e6a4cb3990
commit 81e7223560
226 changed files with 17283 additions and 2744 deletions
+2 -18
View File
@@ -2,15 +2,12 @@ package queryrunner
import (
"context"
"encoding/json"
"log/slog"
resultset "queryorchestration/internal/query/result/set"
"github.com/go-playground/validator/v10"
"github.com/google/uuid"
"github.com/aws/aws-sdk-go-v2/service/sqs/types"
)
const Name = "queryRunner"
@@ -36,21 +33,8 @@ type Body struct {
QueryID uuid.UUID `json:"query_id" validate:"required,uuid"`
}
func (s *Runner) Process(ctx context.Context, req *types.Message) bool {
var body Body
err := json.Unmarshal([]byte(*req.Body), &body)
if err != nil {
slog.Error("parsing body", "messageId", *req.MessageId, "body", *req.Body)
return true
}
err = s.validator.Struct(body)
if err != nil {
slog.Error("invalid body", "messageId", *req.MessageId, "error", err)
return true
}
err = s.svc.ResultSet.Set(ctx, &resultset.Set{
func (s *Runner) Process(ctx context.Context, body Body) bool {
err := s.svc.ResultSet.Set(ctx, &resultset.Set{
DocumentID: body.DocumentID,
QueryID: body.QueryID,
})
+5 -24
View File
@@ -2,7 +2,6 @@ package queryrunner_test
import (
"context"
"encoding/json"
"fmt"
"testing"
@@ -18,7 +17,6 @@ import (
queuemock "queryorchestration/mocks/queue"
"github.com/aws/aws-sdk-go-v2/service/sqs"
"github.com/aws/aws-sdk-go-v2/service/sqs/types"
"github.com/go-playground/validator/v10"
"github.com/google/uuid"
"github.com/pashagolub/pgxmock/v3"
@@ -28,7 +26,7 @@ import (
)
type QueryConfig struct {
runner.BaseConfig
runner.BaseConfig[queryrunner.Body]
queryc.QueryConfig
}
@@ -58,16 +56,10 @@ func TestQueryRunner(t *testing.T) {
assert.NotNil(t, runner)
t.Run("valid", func(t *testing.T) {
doc := resultset.Set{
doc := queryrunner.Body{
DocumentID: uuid.New(),
QueryID: uuid.New(),
}
bodyBytes, err := json.Marshal(doc)
require.NoError(t, err)
body := string(bodyBytes)
msg := &types.Message{
Body: &body,
}
qcfg := "{\"path\":\"examplekey\"}"
reqQuery := uuid.New()
@@ -81,12 +73,11 @@ func TestQueryRunner(t *testing.T) {
DocumentID: doc.DocumentID,
}
cleanEntryId := uuid.New()
textEntryId := uuid.New()
pool.ExpectQuery("name: GetTextEntryByDocId :one").WithArgs(params.DocumentID).
WillReturnRows(
pgxmock.NewRows([]string{"id", "documentId", "bucket", "key", "version", "hash", "cleanEntryId"}).
AddRow(textEntryId, params.DocumentID, "buket", "/i/am/here", int32(1), "example", cleanEntryId),
pgxmock.NewRows([]string{"id", "documentId", "bucket", "key", "hash", "cleanId", "triggerId", "textractJobId", "triggerVersion", "extractionVersion"}).
AddRow(textEntryId, params.DocumentID, "buket", "/i/am/here", "example", uuid.New(), uuid.New(), "jobId", int64(123), int64(543)),
)
pool.ExpectQuery("name: GetQuery :one").WithArgs(query.ID).WillReturnRows(
pgxmock.NewRows([]string{"id", "type", "activeVersion", "latestVersion", "config", "requiredIds"}).
@@ -138,16 +129,6 @@ func TestQueryRunner(t *testing.T) {
).
Return(&sqs.SendMessageOutput{}, nil)
assert.True(t, runner.Process(ctx, msg))
})
t.Run("invalid body", func(t *testing.T) {
body := "definitely invalid"
msgId := "id"
msg := &types.Message{
Body: &body,
MessageId: &msgId,
}
assert.True(t, runner.Process(ctx, msg))
assert.True(t, runner.Process(ctx, doc))
})
}