swagger part 1

This commit is contained in:
jay brown
2025-08-05 07:03:35 -07:00
parent 56fb9b4ab6
commit 3de3d0a7b3
27 changed files with 3128 additions and 92 deletions
+28
View File
@@ -0,0 +1,28 @@
# Document Batch Processing
This directory contains the service layer for managing document batch uploads.
## Purpose
The batch service provides a business logic layer between the HTTP API handlers and the database repository for batch upload operations. It handles:
- **Model Conversion**: Translates between OpenAPI-generated types and internal database models
- **Business Logic**: Encapsulates batch-specific operations (CRUD, progress tracking)
- **Data Validation**: Manages UUID conversions, JSONB parsing, and nullable type handling
## Architecture
```
HTTP Request → API Handler → Batch Service → Database Repository → PostgreSQL
```
The service is **stateless** and **synchronous** - it does not run background processes. Actual document processing happens through the existing Runner pipeline (`storeEventRunner``docInitRunner` → etc.).
## Files
- `service.go` - Main batch service implementation with CRUD operations
- `service_test.go` - Unit tests using testcontainers for database integration
## Usage
The service is instantiated by API handlers in `/api/queryAPI/documents.go` to manage batch upload metadata, progress tracking, and status updates.
+218
View File
@@ -0,0 +1,218 @@
package batch
import (
"context"
"encoding/json"
"fmt"
"time"
"queryorchestration/internal/database/repository"
"queryorchestration/internal/serviceconfig"
"github.com/google/uuid"
"github.com/jackc/pgx/v5/pgtype"
)
// BatchUploadSummary represents a summary of a batch upload
type BatchUploadSummary struct {
ID uuid.UUID `json:"batch_id"`
ClientID string `json:"client_id"`
OriginalFilename string `json:"original_filename"`
Status string `json:"status"`
TotalDocuments int32 `json:"total_documents"`
ProcessedDocuments int32 `json:"processed_documents"`
FailedDocuments int32 `json:"failed_documents"`
InvalidTypeDocuments int32 `json:"invalid_type_documents"`
ProgressPercent int32 `json:"progress_percent"`
CreatedAt time.Time `json:"created_at"`
CompletedAt *time.Time `json:"completed_at,omitempty"`
}
// BatchUploadDetails includes full details with failed filenames
type BatchUploadDetails struct {
BatchUploadSummary
FailedFilenames []string `json:"failed_filenames"`
}
// Service handles batch upload operations
type Service struct {
cfg serviceconfig.ConfigProvider
}
// New creates a new batch service
func New(cfg serviceconfig.ConfigProvider) *Service {
return &Service{
cfg: cfg,
}
}
// Create creates a new batch upload record
func (s *Service) Create(ctx context.Context, clientID string, filename string, totalDocs int32) (uuid.UUID, error) {
return s.cfg.GetDBQueries().CreateBatchUpload(ctx, &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: filename,
TotalDocuments: totalDocs,
})
}
// Get retrieves batch upload details
func (s *Service) Get(ctx context.Context, clientID string, batchID uuid.UUID) (*BatchUploadDetails, error) {
batch, err := s.cfg.GetDBQueries().GetBatchUpload(ctx, &repository.GetBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
if err != nil {
return nil, err
}
return s.convertToDetails(batch), nil
}
// List retrieves all batch uploads for a client with pagination
func (s *Service) List(ctx context.Context, clientID string, limit int32, offset int32) ([]*BatchUploadSummary, error) {
if limit <= 0 {
limit = 20 // default limit
}
if limit > 100 {
limit = 100 // max limit
}
batches, err := s.cfg.GetDBQueries().ListBatchUploads(ctx, &repository.ListBatchUploadsParams{
ClientID: clientID,
Limit: int64(limit),
Offset: int64(offset),
})
if err != nil {
return nil, err
}
summaries := make([]*BatchUploadSummary, len(batches))
for i, batch := range batches {
summaries[i] = s.convertToSummary(batch)
}
return summaries, nil
}
// Cancel cancels a batch upload in progress
func (s *Service) Cancel(ctx context.Context, clientID string, batchID uuid.UUID) error {
return s.cfg.GetDBQueries().CancelBatchUpload(ctx, &repository.CancelBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
}
// UpdateProgress updates batch processing progress
func (s *Service) UpdateProgress(ctx context.Context, clientID string, batchID uuid.UUID, processed, failed, invalidType int32) error {
// Calculate progress percentage
batch, err := s.cfg.GetDBQueries().GetBatchUpload(ctx, &repository.GetBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
if err != nil {
return fmt.Errorf("failed to get batch for progress update: %w", err)
}
total := batch.TotalDocuments
if total == 0 {
return fmt.Errorf("batch has zero total documents")
}
progressPercent := int32(float64(processed+failed+invalidType) / float64(total) * 100)
return s.cfg.GetDBQueries().UpdateBatchProgress(ctx, &repository.UpdateBatchProgressParams{
ID: batchID,
ProcessedDocuments: processed,
FailedDocuments: failed,
InvalidTypeDocuments: invalidType,
ProgressPercent: progressPercent,
})
}
// MarkCompleted marks a batch as completed
func (s *Service) MarkCompleted(ctx context.Context, batchID uuid.UUID) error {
return s.cfg.GetDBQueries().UpdateBatchStatus(ctx, &repository.UpdateBatchStatusParams{
ID: batchID,
Column2: repository.BatchStatusCompleted,
})
}
// MarkFailed marks a batch as failed
func (s *Service) MarkFailed(ctx context.Context, batchID uuid.UUID) error {
return s.cfg.GetDBQueries().UpdateBatchStatus(ctx, &repository.UpdateBatchStatusParams{
ID: batchID,
Column2: repository.BatchStatusFailed,
})
}
// AddFailedFilename adds a failed filename to the batch
func (s *Service) AddFailedFilename(ctx context.Context, batchID uuid.UUID, filename string) error {
return s.cfg.GetDBQueries().AddFailedFilename(ctx, &repository.AddFailedFilenameParams{
ID: batchID,
Column2: filename,
})
}
// convertToDetails converts repository model to service details model
func (s *Service) convertToDetails(batch *repository.BatchUpload) *BatchUploadDetails {
details := &BatchUploadDetails{
BatchUploadSummary: BatchUploadSummary{
ID: batch.ID,
ClientID: batch.ClientID,
OriginalFilename: batch.OriginalFilename,
Status: string(batch.Status),
TotalDocuments: batch.TotalDocuments,
ProcessedDocuments: batch.ProcessedDocuments,
FailedDocuments: batch.FailedDocuments,
InvalidTypeDocuments: batch.InvalidTypeDocuments,
ProgressPercent: batch.ProgressPercent,
CreatedAt: batch.CreatedAt.Time,
},
FailedFilenames: make([]string, 0),
}
if batch.CompletedAt.Valid {
details.CompletedAt = &batch.CompletedAt.Time
}
// Parse failed filenames from JSONB
if len(batch.FailedFilenames) > 0 {
var filenames []string
if err := json.Unmarshal(batch.FailedFilenames, &filenames); err == nil {
details.FailedFilenames = filenames
}
}
return details
}
// convertToSummary converts repository list row to service summary model
func (s *Service) convertToSummary(batch *repository.ListBatchUploadsRow) *BatchUploadSummary {
summary := &BatchUploadSummary{
ID: batch.ID,
ClientID: batch.ClientID,
OriginalFilename: batch.OriginalFilename,
Status: string(batch.Status),
TotalDocuments: batch.TotalDocuments,
ProcessedDocuments: batch.ProcessedDocuments,
FailedDocuments: batch.FailedDocuments,
InvalidTypeDocuments: batch.InvalidTypeDocuments,
ProgressPercent: batch.ProgressPercent,
CreatedAt: s.pgTimestampToTime(batch.CreatedAt),
}
if batch.CompletedAt.Valid {
t := s.pgTimestampToTime(batch.CompletedAt)
summary.CompletedAt = &t
}
return summary
}
// pgTimestampToTime converts pgtype.Timestamp to time.Time
func (s *Service) pgTimestampToTime(ts pgtype.Timestamp) time.Time {
if ts.Valid {
return ts.Time
}
return time.Time{}
}
+185
View File
@@ -0,0 +1,185 @@
package batch_test
import (
"testing"
"queryorchestration/internal/database/repository"
documentbatch "queryorchestration/internal/document/batch"
"queryorchestration/internal/serviceconfig"
"queryorchestration/internal/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type TestConfig struct {
serviceconfig.BaseConfig
}
func TestUpdateProgress(t *testing.T) {
cfg := &TestConfig{}
test.CreateDB(t, cfg)
service := documentbatch.New(cfg)
// Create test client
clientID := "test_client_progress"
err := cfg.GetDBQueries().CreateClient(t.Context(), &repository.CreateClientParams{
Clientid: clientID,
Name: "Test Client Progress",
})
require.NoError(t, err)
// Create test batch with total documents
batchID, err := cfg.GetDBQueries().CreateBatchUpload(t.Context(), &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: "test.zip",
TotalDocuments: 10,
})
require.NoError(t, err)
// Test updating progress
err = service.UpdateProgress(t.Context(), clientID, batchID, 5, 2, 1)
require.NoError(t, err)
// Verify progress was updated
batch, err := cfg.GetDBQueries().GetBatchUpload(t.Context(), &repository.GetBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
require.NoError(t, err)
assert.Equal(t, int32(5), batch.ProcessedDocuments)
assert.Equal(t, int32(2), batch.FailedDocuments)
assert.Equal(t, int32(1), batch.InvalidTypeDocuments)
assert.Equal(t, int32(80), batch.ProgressPercent) // (5+2+1)/10 * 100 = 80%
}
func TestUpdateProgressZeroTotalDocuments(t *testing.T) {
cfg := &TestConfig{}
test.CreateDB(t, cfg)
service := documentbatch.New(cfg)
// Create test client
clientID := "test_client_zero"
err := cfg.GetDBQueries().CreateClient(t.Context(), &repository.CreateClientParams{
Clientid: clientID,
Name: "Test Client Zero",
})
require.NoError(t, err)
// Create test batch with zero total documents
batchID, err := cfg.GetDBQueries().CreateBatchUpload(t.Context(), &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: "test.zip",
TotalDocuments: 0,
})
require.NoError(t, err)
// Test updating progress should fail with zero total documents
err = service.UpdateProgress(t.Context(), clientID, batchID, 5, 2, 1)
require.Error(t, err)
assert.Contains(t, err.Error(), "batch has zero total documents")
}
func TestMarkCompleted(t *testing.T) {
cfg := &TestConfig{}
test.CreateDB(t, cfg)
service := documentbatch.New(cfg)
// Create test client
clientID := "test_client_complete"
err := cfg.GetDBQueries().CreateClient(t.Context(), &repository.CreateClientParams{
Clientid: clientID,
Name: "Test Client Complete",
})
require.NoError(t, err)
// Create test batch
batchID, err := cfg.GetDBQueries().CreateBatchUpload(t.Context(), &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: "test.zip",
TotalDocuments: 10,
})
require.NoError(t, err)
// Test marking as completed
err = service.MarkCompleted(t.Context(), batchID)
require.NoError(t, err)
// Verify status was updated
batch, err := cfg.GetDBQueries().GetBatchUpload(t.Context(), &repository.GetBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
require.NoError(t, err)
assert.Equal(t, repository.BatchStatusCompleted, batch.Status)
}
func TestMarkFailed(t *testing.T) {
cfg := &TestConfig{}
test.CreateDB(t, cfg)
service := documentbatch.New(cfg)
// Create test client
clientID := "test_client_failed"
err := cfg.GetDBQueries().CreateClient(t.Context(), &repository.CreateClientParams{
Clientid: clientID,
Name: "Test Client Failed",
})
require.NoError(t, err)
// Create test batch
batchID, err := cfg.GetDBQueries().CreateBatchUpload(t.Context(), &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: "test.zip",
TotalDocuments: 10,
})
require.NoError(t, err)
// Test marking as failed
err = service.MarkFailed(t.Context(), batchID)
require.NoError(t, err)
// Verify status was updated
batch, err := cfg.GetDBQueries().GetBatchUpload(t.Context(), &repository.GetBatchUploadParams{
ID: batchID,
ClientID: clientID,
})
require.NoError(t, err)
assert.Equal(t, repository.BatchStatusFailed, batch.Status)
}
func TestAddFailedFilename(t *testing.T) {
cfg := &TestConfig{}
test.CreateDB(t, cfg)
service := documentbatch.New(cfg)
// Create test client
clientID := "test_client_filename"
err := cfg.GetDBQueries().CreateClient(t.Context(), &repository.CreateClientParams{
Clientid: clientID,
Name: "Test Client Filename",
})
require.NoError(t, err)
// Create test batch
batchID, err := cfg.GetDBQueries().CreateBatchUpload(t.Context(), &repository.CreateBatchUploadParams{
ClientID: clientID,
OriginalFilename: "test.zip",
TotalDocuments: 10,
})
require.NoError(t, err)
// Test adding failed filename
err = service.AddFailedFilename(t.Context(), batchID, "failed_file.pdf")
require.NoError(t, err)
// Get the full details to check failed filenames
details, err := service.Get(t.Context(), clientID, batchID)
require.NoError(t, err)
assert.Contains(t, details.FailedFilenames, "failed_file.pdf")
}