refactor: implement bidirectional transformation support with PostgreSQL integration

internal/app/etl/transformers/plan.go

@@ -59,6 +59,49 @@ func computeTransformationPlan(columns []models.ColumnType) []etl.ColumnTransfor
 	return plan
 }
 
+func computePostgresTransformationPlan(columns []models.ColumnType) []etl.ColumnTransformPlan {
+	var plan []etl.ColumnTransformPlan
+
+	for i, col := range columns {
+		switch col.SystemType() {
+		case "uuid":
+			plan = append(plan, etl.ColumnTransformPlan{
+				Index: i,
+				Fn: func(v any) (any, error) {
+					if b, ok := v.([]byte); ok && b != nil {
+						return bigEndianToMssqlUuid(b)
+					}
+					return v, nil
+				},
+			})
+
+		case "geometry":
+			plan = append(plan, etl.ColumnTransformPlan{
+				Index: i,
+				Fn: func(v any) (any, error) {
+					if b, ok := v.([]byte); ok && b != nil {
+						return ewkbToMssqlGeo(b, false)
+					}
+					return v, nil
+				},
+			})
+
+		case "geography":
+			plan = append(plan, etl.ColumnTransformPlan{
+				Index: i,
+				Fn: func(v any) (any, error) {
+					if b, ok := v.([]byte); ok && b != nil {
+						return ewkbToMssqlGeo(b, true)
+					}
+					return v, nil
+				},
+			})
+		}
+	}
+
+	return plan
+}
+
 func computeStorageTransformationPlan(
 	ctx context.Context,
 	azureClient *azure.Client,

internal/app/etl/transformers/postgres.go

@@ -0,0 +1,72 @@
+package transformers
+
+import (
+	"context"
+	"sync"
+
+	"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
+	"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
+	"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl"
+	"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
+)
+
+type PostgresTransformer struct {
+	sourceTable config.SourceTableInfo
+}
+
+func NewPostgresTransformer(sourceTable config.SourceTableInfo) etl.Transformer {
+	return &PostgresTransformer{sourceTable: sourceTable}
+}
+
+func (pgTr *PostgresTransformer) Consume(
+	ctx context.Context,
+	columns []models.ColumnType,
+	retryConfig config.RetryConfig,
+	batchSize int,
+	chBatchesIn <-chan models.Batch,
+	chBatchesOut chan<- models.Batch,
+	chJobErrorsOut chan<- custom_errors.JobError,
+	wgActiveBatches *sync.WaitGroup,
+) {
+	transformationPlan := computePostgresTransformationPlan(columns)
+
+	acc := &batchAccumulator{batchSize: batchSize}
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+
+		case batch, ok := <-chBatchesIn:
+			if !ok {
+				acc.flush(ctx, chBatchesOut, wgActiveBatches)
+				return
+			}
+
+			if len(transformationPlan) > 0 {
+				if err := ProcessBatchWithRetries(ctx, &batch, transformationPlan, retryConfig); err != nil {
+					sendTransformError(ctx, err, chJobErrorsOut)
+					return
+				}
+			}
+
+			if batchSize <= 0 {
+				wgActiveBatches.Add(1)
+				select {
+				case chBatchesOut <- batch:
+				case <-ctx.Done():
+					wgActiveBatches.Done()
+					return
+				}
+				continue
+			}
+
+			acc.add(batch)
+			if acc.ready() {
+				if !acc.flush(ctx, chBatchesOut, wgActiveBatches) {
+					return
+				}
+			}
+		}
+	}
+}

internal/app/etl/transformers/utils.go

@@ -4,6 +4,8 @@ import (
 	"encoding/binary"
 	"errors"
 	"time"
+
+	mssqlclrgeo "github.com/gaspardle/go-mssqlclrgeo"
 )
 
 func mssqlUuidToBigEndian(mssqlUuid []byte) ([]byte, error) {
@@ -62,6 +64,51 @@ func ensureUTC(t time.Time) time.Time {
 	return time.Date(t.Year(), t.Month(), t.Day(), t.Hour(), t.Minute(), t.Second(), t.Nanosecond(), time.UTC)
 }
 
+func bigEndianToMssqlUuid(pgUuid []byte) ([]byte, error) {
+	if len(pgUuid) != 16 {
+		return nil, errors.New("Invalid uuid")
+	}
+
+	mssqlUuid := make([]byte, 16)
+	mssqlUuid[0], mssqlUuid[1], mssqlUuid[2], mssqlUuid[3] = pgUuid[3], pgUuid[2], pgUuid[1], pgUuid[0]
+	mssqlUuid[4], mssqlUuid[5] = pgUuid[5], pgUuid[4]
+	mssqlUuid[6], mssqlUuid[7] = pgUuid[7], pgUuid[6]
+	copy(mssqlUuid[8:], pgUuid[8:])
+
+	return mssqlUuid, nil
+}
+
+func ewkbToMssqlGeo(ewkb []byte, isGeography bool) ([]byte, error) {
+	if len(ewkb) < 5 {
+		return nil, errors.New("Invalid ewkb")
+	}
+
+	var byteOrder binary.ByteOrder
+	if ewkb[0] == 0 {
+		byteOrder = binary.BigEndian
+	} else {
+		byteOrder = binary.LittleEndian
+	}
+
+	wkbType := byteOrder.Uint32(ewkb[1:5])
+
+	var wkb []byte
+	if wkbType&sridFlag != 0 {
+		if len(ewkb) < 9 {
+			return nil, errors.New("Invalid ewkb: SRID flag set but data too short")
+		}
+		clearType := wkbType &^ uint32(sridFlag)
+		wkb = make([]byte, len(ewkb)-4)
+		wkb[0] = ewkb[0]
+		byteOrder.PutUint32(wkb[1:5], clearType)
+		copy(wkb[5:], ewkb[9:])
+	} else {
+		wkb = ewkb
+	}
+
+	return mssqlclrgeo.WkbToUdtGeo(wkb, isGeography)
+}
+
 func ToInt64(v any) (int64, bool) {
 	switch t := v.(type) {
 	case int: