batch upload impl

api/queryAPI/documents.go

@@ -5,6 +5,7 @@ import (
 	"log/slog"
 	"net/http"
 
+	"queryorchestration/internal/document/batch/storage"
 	documentupload "queryorchestration/internal/document/upload"
 
 	"github.com/google/uuid"
@@ -128,48 +129,70 @@ func (s *Controllers) ListDocumentBatches(ctx echo.Context, clientId ClientID, p
 
 // UploadDocumentBatch handles ZIP archive upload containing multiple PDFs
 func (s *Controllers) UploadDocumentBatch(ctx echo.Context, clientId ClientID) error {
-	// Get the multipart form
-	form, err := ctx.MultipartForm()
+	// Parse multipart form to get ZIP file
+	file, err := ctx.FormFile("archive")
 	if err != nil {
-		slog.Error("unable to get form data", "error", err)
-		return echo.NewHTTPError(http.StatusBadRequest, "unable to get form data")
+		slog.Error("failed to get uploaded file", "error", err, "client_id", clientId)
+		return echo.NewHTTPError(http.StatusBadRequest, "file upload required")
 	}
 
-	// Get the archive file
-	files := form.File["archive"]
-	if len(files) == 0 {
-		return echo.NewHTTPError(http.StatusBadRequest, "missing archive file")
-	} else if len(files) > 1 {
-		return echo.NewHTTPError(http.StatusBadRequest, "too many files")
-	}
-	file := files[0]
-
-	// Skip ZIP validation for tests - in production this would check file content
-	// if file.Header.Get("Content-Type") != "application/zip" {
-	//	return echo.NewHTTPError(http.StatusBadRequest, "file must be a ZIP archive")
-	// }
-
-	// For now, we'll create a batch record with placeholder total documents
-	// In the real implementation, we would:
-	// 1. Store the ZIP file to S3
-	// 2. Start an async process to extract and process PDFs
-	// 3. Return immediately with 202 Accepted
-
-	// Create batch record
-	batchID, err := s.svc.DocumentBatch.Create(ctx.Request().Context(), clientId, file.Filename, 0)
+	// Open uploaded file
+	src, err := file.Open()
 	if err != nil {
-		slog.Error("unable to create batch", "error", err)
-		return echo.NewHTTPError(http.StatusInternalServerError, "unable to create batch")
+		slog.Error("failed to open uploaded file", "error", err, "client_id", clientId)
+		return echo.NewHTTPError(http.StatusInternalServerError, "failed to process uploaded file")
+	}
+	defer src.Close()
+
+	// Initialize storage service with objectstore config
+	storageService := storage.New(s.cfg)
+
+	// Validate ZIP file
+	err = storageService.ValidateZIPFile(file.Filename, file.Size)
+	if err != nil {
+		slog.Error("ZIP validation failed", "filename", file.Filename, "size", file.Size, "error", err, "client_id", clientId)
+		return echo.NewHTTPError(http.StatusBadRequest, fmt.Sprintf("invalid ZIP file: %v", err))
 	}
 
-	// Build response
+	// Store ZIP file to S3
+	storageResult, err := storageService.StoreZIPFile(ctx.Request().Context(), string(clientId), file.Filename, src)
+	if err != nil {
+		slog.Error("failed to store ZIP file", "error", err, "client_id", clientId)
+		return echo.NewHTTPError(http.StatusInternalServerError, "failed to store ZIP file")
+	}
+
+	// Create batch record with storage metadata
+	// Note: totalDocs is unknown at this point, will be determined during extraction in later parts
+	batchID, err := s.svc.DocumentBatch.CreateWithStorage(
+		ctx.Request().Context(),
+		string(clientId),
+		file.Filename,
+		0, // totalDocs unknown in Part 1
+		storageResult.Bucket,
+		storageResult.Key,
+		storageResult.SizeBytes,
+	)
+	if err != nil {
+		slog.Error("failed to create batch record", "error", err, "client_id", clientId)
+		return echo.NewHTTPError(http.StatusInternalServerError, "failed to create batch record")
+	}
+
+	slog.Info("ZIP batch upload completed",
+		"batch_id", batchID,
+		"filename", file.Filename,
+		"size_bytes", storageResult.SizeBytes,
+		"s3_key", storageResult.Key,
+		"client_id", clientId,
+	)
+
+	// Return 202 Accepted with batch ID and status URL
+	statusUrl := fmt.Sprintf("/clients/%s/documents/batches/%s", clientId, batchID)
 	response := BatchUploadResponse{
 		BatchId:   BatchID(batchID),
-		Status:    BatchStatusProcessing,
-		StatusUrl: fmt.Sprintf("/client/%s/document/batch/%s", clientId, batchID.String()),
+		Status:    "processing",
+		StatusUrl: statusUrl,
 	}
 
-	// Return 202 Accepted for async processing
 	return ctx.JSON(http.StatusAccepted, response)
 }