2 Commits

16 changed files with 411 additions and 354 deletions

View File

@@ -1,77 +0,0 @@
package main
import (
"context"
"database/sql"
"errors"
"fmt"
"sync"
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"github.com/jackc/pgx/v5/pgxpool"
_ "github.com/microsoft/go-mssqldb"
log "github.com/sirupsen/logrus"
)
func connectToSqlServer() (*sql.DB, error) {
db, err := sql.Open("sqlserver", config.App.SourceDbUrl)
if err != nil {
return nil, fmt.Errorf("Unable to connect to sqlserver: %w", err)
}
ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
defer cancel()
if err := db.PingContext(ctx); err != nil {
return nil, fmt.Errorf("Unable to ping sqlserver: %w", err)
}
return db, nil
}
func connectToPostgres() (*pgxpool.Pool, error) {
ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
defer cancel()
pool, err := pgxpool.New(ctx, config.App.TargetDbUrl)
if err != nil {
return nil, fmt.Errorf("Unable to connect to postgres: %w", err)
}
if err := pool.Ping(ctx); err != nil {
pool.Close()
return nil, fmt.Errorf("Unable to ping postgres: %w", err)
}
return pool, nil
}
func connectToDatabases() (*sql.DB, *pgxpool.Pool, error) {
var sourceDbErr, targetDbErr error
var sourceDb *sql.DB
var targetDb *pgxpool.Pool
var wg sync.WaitGroup
wg.Go(func() {
sourceDb, sourceDbErr = connectToSqlServer()
if sourceDbErr != nil {
log.Error("Unable to connect to source db: ", sourceDbErr)
}
})
wg.Go(func() {
targetDb, targetDbErr = connectToPostgres()
if targetDbErr != nil {
log.Error("Unable to connect to target db: ", targetDbErr)
}
})
wg.Wait()
if sourceDbErr != nil || targetDbErr != nil {
return nil, nil, errors.New("Unable to connect to databases")
}
return sourceDb, targetDb, nil
}

View File

@@ -11,6 +11,7 @@ import (
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/loaders"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/table_analyzers"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/transformers"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
log "github.com/sirupsen/logrus"
"golang.org/x/sync/errgroup"
)
@@ -95,10 +96,10 @@ func processMigrationJobs(
targetDb dbwrapper.DbWrapper,
jobs []config.Job,
maxParallelWorkers int,
) []JobResult {
) []models.JobResult {
if len(jobs) == 0 {
log.Info("No migration jobs configured")
return []JobResult{}
return []models.JobResult{}
}
if maxParallelWorkers <= 0 {
@@ -111,7 +112,7 @@ func processMigrationJobs(
log.Infof("Starting migration with %d parallel worker(s)", maxParallelWorkers)
chJobResults := make(chan JobResult, len(jobs))
chJobResults := make(chan models.JobResult, len(jobs))
chJobs := make(chan config.Job, len(jobs))
var wgJobs sync.WaitGroup
@@ -151,7 +152,7 @@ func processMigrationJobs(
close(chJobResults)
}()
var finalResults []JobResult
var finalResults []models.JobResult
for res := range chJobResults {
finalResults = append(finalResults, res)
}

View File

@@ -1,13 +0,0 @@
package main
import "time"
type JobResult struct {
JobName string
StartTime time.Time
Duration time.Duration
RowsRead int64
RowsLoaded int64
RowsFailed int64
Error error
}

View File

@@ -11,7 +11,6 @@ import (
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
dbwrapper "git.ksdemosapps.com/kylesoda/go-migrate/internal/app/db-wrapper"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/extractors"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/table_analyzers"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
log "github.com/sirupsen/logrus"
@@ -27,11 +26,11 @@ func processMigrationJob(
transformer etl.Transformer,
loader etl.Loader,
job config.Job,
) JobResult {
) models.JobResult {
localCtx, cancel := context.WithCancel(ctx)
defer cancel()
result := JobResult{
result := models.JobResult{
JobName: job.Name,
StartTime: time.Now(),
}
@@ -86,6 +85,7 @@ func processMigrationJob(
}
chJobErrors := make(chan custom_errors.JobError, job.QueueSize)
chExtractorErrors := make(chan custom_errors.ExtractorError, job.QueueSize)
chLoadersErrors := make(chan custom_errors.LoaderError, job.QueueSize)
chPartitions := make(chan models.Partition, job.QueueSize)
chBatchesRaw := make(chan models.Batch, job.QueueSize)
@@ -105,6 +105,15 @@ func processMigrationJob(
}
}()
go custom_errors.ExtractorErrorHandler(
localCtx,
job.Retry,
job.MaxPartitionErrrors,
chExtractorErrors,
chPartitions,
chJobErrors,
&wgActivePartitions,
)
go custom_errors.LoaderErrorHandler(
localCtx,
job.Retry,
@@ -120,14 +129,14 @@ func processMigrationJob(
for range maxExtractors {
wgExtractors.Go(func() {
extractors.Consume(
extractor.Exec(
localCtx,
extractor,
job.SourceTable,
sourceColTypes,
job.BatchSize,
chPartitions,
chBatchesRaw,
chExtractorErrors,
chJobErrors,
&wgActivePartitions,
&rowsRead,
@@ -181,6 +190,8 @@ func processMigrationJob(
log.Debugf("wgActivePartitions is empty (%v)", job.Name)
close(chPartitions)
log.Debugf("chPartitions is closed (%v)", job.Name)
close(chExtractorErrors)
log.Debugf("chExtractorErrors is closed (%v)", job.Name)
wgExtractors.Wait()
log.Debugf("wgExtractors is empty (%v)", job.Name)

2
go.mod
View File

@@ -15,6 +15,8 @@ require (
)
require (
github.com/cenkalti/backoff v2.2.1+incompatible // indirect
github.com/cenkalti/backoff/v5 v5.0.3 // indirect
github.com/golang-sql/civil v0.0.0-20220223132316-b832511892a9 // indirect
github.com/golang-sql/sqlexp v0.1.0 // indirect
github.com/jackc/pgpassfile v1.0.0 // indirect

4
go.sum
View File

@@ -16,6 +16,10 @@ github.com/alecthomas/assert/v2 v2.10.0 h1:jjRCHsj6hBJhkmhznrCzoNpbA3zqy0fYiUcYZ
github.com/alecthomas/assert/v2 v2.10.0/go.mod h1:Bze95FyfUr7x34QZrjL+XP+0qgp/zg8yS+TtBj1WA3k=
github.com/alecthomas/repr v0.4.0 h1:GhI2A8MACjfegCPVq9f1FLvIBS+DrQ2KQBFZP1iFzXc=
github.com/alecthomas/repr v0.4.0/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
github.com/cenkalti/backoff v2.2.1+incompatible h1:tNowT99t7UNflLxfYYSlKYsBpXdEet03Pg2g16Swow4=
github.com/cenkalti/backoff v2.2.1+incompatible/go.mod h1:90ReRw6GdpyfrHakVjL/QHaoyV4aDUVVkXQJJJ3NXXM=
github.com/cenkalti/backoff/v5 v5.0.3 h1:ZN+IMa753KfX5hd8vVaMixjnqRZ3y8CuJKRKj1xcsSM=
github.com/cenkalti/backoff/v5 v5.0.3/go.mod h1:rkhZdG3JZukswDf7f0cwqPNk4K0sa+F97BxZthm/crw=
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=

View File

@@ -1,7 +1,13 @@
package custom_errors
import (
"context"
"fmt"
"sync"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
"github.com/google/uuid"
)
type ExtractorError struct {
@@ -14,3 +20,100 @@ type ExtractorError struct {
func (e *ExtractorError) Error() string {
return e.Msg
}
func ExtractorErrorHandler(
ctx context.Context,
retryConfig config.RetryConfig,
maxPartitionErrors int,
chErrorsIn <-chan ExtractorError,
chPartitionsOut chan<- models.Partition,
chJobErrorsOut chan<- JobError,
wgActivePartitions *sync.WaitGroup,
) {
definitiveErrors := 0
for {
if ctx.Err() != nil {
return
}
select {
case <-ctx.Done():
return
case err, ok := <-chErrorsIn:
if !ok {
return
}
if err.Partition.RetryCounter >= retryConfig.Attempts {
wgActivePartitions.Done()
definitiveErrors++
jobError := JobError{
ShouldCancelJob: false,
Msg: fmt.Sprintf("Partition %v reached max retries (%d)", err.Partition.Id, retryConfig.Attempts),
Prev: &err,
}
select {
case chJobErrorsOut <- jobError:
case <-ctx.Done():
return
}
if maxPartitionErrors > 0 && definitiveErrors >= maxPartitionErrors {
fatalError := JobError{
ShouldCancelJob: true,
Msg: fmt.Sprintf("Partition error limit reached (%d)", maxPartitionErrors),
Prev: &err,
}
select {
case chJobErrorsOut <- fatalError:
case <-ctx.Done():
return
}
}
continue
} else {
jobError := JobError{
ShouldCancelJob: false,
Msg: fmt.Sprintf("Temporal error in partition %v (retries: %d)", err.Partition.Id, err.Partition.RetryCounter),
Prev: &err,
}
select {
case chJobErrorsOut <- jobError:
case <-ctx.Done():
return
}
}
newPartition := err.Partition
newPartition.RetryCounter++
delay := computeBackoffDelay(
newPartition.RetryCounter,
retryConfig.BaseDelayMs,
retryConfig.MaxDelayMs,
retryConfig.MaxJitterMs,
)
if err.HasLastId {
newPartition.ParentId = err.Partition.Id
newPartition.Id = uuid.New()
newPartition.Range.Min = err.LastId
newPartition.Range.IsMinInclusive = false
}
requeueWithBackoff(ctx, delay, func() {
select {
case chPartitionsOut <- newPartition:
case <-ctx.Done():
return
}
})
}
}
}

View File

@@ -1,92 +0,0 @@
package extractors
import (
"context"
"errors"
"slices"
"strings"
"sync"
"sync/atomic"
"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"
)
func Consume(
ctx context.Context,
extractor etl.Extractor,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
chErrorsOut chan<- custom_errors.JobError,
wgActivePartitions *sync.WaitGroup,
rowsRead *int64,
) {
indexPrimaryKey := slices.IndexFunc(columns, func(col models.ColumnType) bool {
return strings.EqualFold(col.Name(), tableInfo.PrimaryKey)
})
if indexPrimaryKey == -1 {
select {
case <-ctx.Done():
return
case chErrorsOut <- custom_errors.JobError{
ShouldCancelJob: true,
Msg: "Primary key not found in provided columns",
}:
}
return
}
for {
if ctx.Err() != nil {
return
}
select {
case <-ctx.Done():
return
case partition, ok := <-chPartitionsIn:
if !ok {
return
}
rowsReadResult, err := extractWithRetries(
ctx,
extractor,
tableInfo,
columns,
batchSize,
partition,
indexPrimaryKey,
chBatchesOut,
)
wgActivePartitions.Done()
if rowsReadResult > 0 {
atomic.AddInt64(rowsRead, rowsReadResult)
}
if err != nil {
var jobError *custom_errors.JobError
if errors.As(err, &jobError) {
select {
case <-ctx.Done():
return
case chErrorsOut <- *jobError:
}
} else {
select {
case <-ctx.Done():
return
case chErrorsOut <- custom_errors.JobError{ShouldCancelJob: false, Msg: err.Error(), Prev: err}:
}
}
}
}
}
}

View File

@@ -1,70 +0,0 @@
package extractors
import (
"context"
"errors"
"fmt"
"time"
"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"
"github.com/google/uuid"
)
func extractWithRetries(
ctx context.Context,
extractor etl.Extractor,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error) {
var totalRowsRead int64
delay := time.Duration(time.Second * 1)
currentParitition := partition
for {
rowsRead, err := extractor.Exec(
ctx,
tableInfo,
columns,
batchSize,
currentParitition,
indexPrimaryKey,
chBatchesOut,
)
totalRowsRead += rowsRead
if err == nil {
return totalRowsRead, nil
}
var exError *custom_errors.ExtractorError
if errors.As(err, &exError) {
currentParitition.RetryCounter++
if currentParitition.RetryCounter > 3 {
return totalRowsRead, &custom_errors.JobError{
Msg: fmt.Sprintf("Partition %v reached max retries", exError.Partition.Id),
Prev: err,
}
}
if exError.HasLastId {
currentParitition.ParentId = exError.Partition.Id
currentParitition.Id = uuid.New()
currentParitition.Range.Min = exError.LastId
currentParitition.Range.IsMinInclusive = false
}
time.Sleep(delay)
continue
}
return totalRowsRead, err
}
}

View File

@@ -1,64 +0,0 @@
package extractors
import (
"context"
"fmt"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/convert"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
"github.com/google/uuid"
)
func errorFromLastPartitionRow(
lastRow models.UnknownRowValues,
indexPrimaryKey int,
partition models.Partition,
previousError error,
) error {
lastIdRawValue := lastRow[indexPrimaryKey]
lastId, ok := convert.ToInt64(lastIdRawValue)
if !ok {
currentPartition := partition
currentPartition.RetryCounter = 3
return &custom_errors.ExtractorError{
Partition: currentPartition,
HasLastId: true,
Msg: fmt.Sprintf("Couldn't cast last id value as int: %s", previousError.Error()),
}
}
return &custom_errors.ExtractorError{
Partition: partition,
HasLastId: true,
LastId: lastId,
Msg: previousError.Error(),
}
}
func sendBatch(ctx context.Context, chBatchesOut chan<- models.Batch, batch models.Batch) error {
select {
case chBatchesOut <- batch:
return nil
case <-ctx.Done():
return ctx.Err()
}
}
func flush(
ctx context.Context,
partition *models.Partition,
batchSize int,
batchRows []models.UnknownRowValues,
chBatchesOut chan<- models.Batch,
) error {
if len(batchRows) == 0 {
return nil
}
batch := models.Batch{Id: uuid.New(), PartitionId: partition.Id, Rows: batchRows}
batchRows = make([]models.UnknownRowValues, 0, batchSize)
return sendBatch(ctx, chBatchesOut, batch)
}

View File

@@ -3,13 +3,20 @@ package extractors
import (
"context"
"database/sql"
"errors"
"fmt"
"slices"
"strings"
"sync"
"sync/atomic"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/convert"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
dbwrapper "git.ksdemosapps.com/kylesoda/go-migrate/internal/app/db-wrapper"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
"github.com/google/uuid"
)
type MssqlExtractor struct {
@@ -64,7 +71,35 @@ func buildExtractQueryMssql(
return sbQuery.String()
}
func (mssqlEx *MssqlExtractor) Exec(
func errorFromLastRow(
lastRow models.UnknownRowValues,
indexPrimaryKey int,
partition models.Partition,
previousError error,
) *custom_errors.ExtractorError {
lastIdRawValue := lastRow[indexPrimaryKey]
lastId, ok := convert.ToInt64(lastIdRawValue)
if !ok {
currentPartition := partition
currentPartition.RetryCounter = 3
return &custom_errors.ExtractorError{
Partition: currentPartition,
HasLastId: true,
Msg: fmt.Sprintf("Couldn't cast last id value as int: %s", previousError.Error()),
}
}
return &custom_errors.ExtractorError{
Partition: partition,
HasLastId: true,
LastId: lastId,
Msg: previousError.Error(),
}
}
func (mssqlEx *MssqlExtractor) ProcessPartition(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -72,50 +107,171 @@ func (mssqlEx *MssqlExtractor) Exec(
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error) {
) (int, error) {
query := buildExtractQueryMssql(tableInfo, columns, partition.HasRange, partition.Range.IsMinInclusive)
var queryArgs []any
if partition.HasRange {
queryArgs = append(queryArgs, sql.Named("min", partition.Range.Min), sql.Named("max", partition.Range.Max))
queryArgs = append(queryArgs,
sql.Named("min", partition.Range.Min),
sql.Named("max", partition.Range.Max),
)
}
rowsRead := 0
rows, err := mssqlEx.db.Query(ctx, query, queryArgs...)
if err != nil {
return 0, err
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
}
defer rows.Close()
batchRows := make([]models.UnknownRowValues, 0, batchSize)
var rowsRead int64 = 0
for rows.Next() {
values, err := rows.Values()
if err != nil {
if len(batchRows) == 0 {
return rowsRead, err
rowValues := make([]any, len(columns))
scanArgs := make([]any, len(columns))
for i := range rowValues {
scanArgs[i] = &rowValues[i]
}
if err := flush(ctx, &partition, batchSize, batchRows, chBatchesOut); err != nil {
return rowsRead, err
if err := rows.Scan(scanArgs...); err != nil {
if len(batchRows) == 0 {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
}
lastRow := batchRows[len(batchRows)-1]
return rowsRead, errorFromLastPartitionRow(lastRow, indexPrimaryKey, partition, err)
select {
case chBatchesOut <- models.Batch{Id: uuid.New(), PartitionId: partition.Id, Rows: batchRows, RetryCounter: 0}:
case <-ctx.Done():
return rowsRead, ctx.Err()
}
return rowsRead, errorFromLastRow(lastRow, indexPrimaryKey, partition, err)
}
rowsRead++
batchRows = append(batchRows, values)
batchRows = append(batchRows, rowValues)
if len(batchRows) >= batchSize {
if err := flush(ctx, &partition, batchSize, batchRows, chBatchesOut); err != nil {
return rowsRead, err
select {
case chBatchesOut <- models.Batch{Id: uuid.New(), PartitionId: partition.Id, Rows: batchRows, RetryCounter: 0}:
case <-ctx.Done():
return rowsRead, ctx.Err()
}
batchRows = make([]models.UnknownRowValues, 0, batchSize)
}
}
if err := rows.Err(); err != nil {
if errors.Is(err, ctx.Err()) {
return rowsRead, ctx.Err()
}
if len(batchRows) > 0 {
lastRow := batchRows[len(batchRows)-1]
return rowsRead, errorFromLastRow(lastRow, indexPrimaryKey, partition, err)
}
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
}
if len(batchRows) > 0 {
select {
case chBatchesOut <- models.Batch{Id: uuid.New(), PartitionId: partition.Id, Rows: batchRows, RetryCounter: 0}:
case <-ctx.Done():
return rowsRead, ctx.Err()
}
}
if err := flush(ctx, &partition, batchSize, batchRows, chBatchesOut); err != nil {
return rowsRead, err
}
return rowsRead, rows.Err()
return rowsRead, nil
}
func (mssqlEx *MssqlExtractor) Exec(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
chErrorsOut chan<- custom_errors.ExtractorError,
chJobErrorsOut chan<- custom_errors.JobError,
wgActivePartitions *sync.WaitGroup,
rowsRead *int64,
) {
indexPrimaryKey := slices.IndexFunc(columns, func(col models.ColumnType) bool {
return strings.EqualFold(col.Name(), tableInfo.PrimaryKey)
})
if indexPrimaryKey == -1 {
select {
case <-ctx.Done():
return
case chJobErrorsOut <- custom_errors.JobError{
ShouldCancelJob: true,
Msg: "Primary key not found in provided columns",
}:
}
return
}
for {
if ctx.Err() != nil {
return
}
select {
case <-ctx.Done():
return
case partition, ok := <-chPartitionsIn:
if !ok {
return
}
rowsReadResult, err := mssqlEx.ProcessPartition(
ctx,
tableInfo,
columns,
batchSize,
partition,
indexPrimaryKey,
chBatchesOut,
)
if rowsReadResult > 0 {
atomic.AddInt64(rowsRead, int64(rowsReadResult))
}
if err != nil {
var exError *custom_errors.ExtractorError
var jobError *custom_errors.JobError
if errors.As(err, &exError) {
select {
case <-ctx.Done():
return
case chErrorsOut <- *exError:
}
} else if errors.As(err, &jobError) {
select {
case <-ctx.Done():
return
case chJobErrorsOut <- *jobError:
}
} else {
select {
case <-ctx.Done():
return
case chErrorsOut <- custom_errors.ExtractorError{Partition: partition, Msg: err.Error()}:
}
}
continue
}
wgActivePartitions.Done()
}
}
}

View File

@@ -5,6 +5,7 @@ import (
"errors"
"fmt"
"strings"
"sync"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
@@ -50,7 +51,7 @@ func buildExtractQueryPostgres(sourceDbInfo config.SourceTableInfo, columns []mo
return fmt.Sprintf(`SELECT %s FROM "%s"."%s" ORDER BY "%s" ASC`, sbColumns.String(), sourceDbInfo.Schema, sourceDbInfo.Table, sourceDbInfo.PrimaryKey)
}
func (postgresEx *PostgresExtractor) Exec(
func (postgresEx *PostgresExtractor) ProcessPartition(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -58,14 +59,14 @@ func (postgresEx *PostgresExtractor) Exec(
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error) {
) (int, error) {
query := buildExtractQueryPostgres(tableInfo, columns)
if partition.HasRange {
return 0, errors.New("Batch config not yet supported")
}
var rowsRead int64 = 0
rowsRead := 0
rows, err := postgresEx.db.Query(ctx, query)
if err != nil {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
@@ -108,3 +109,17 @@ func (postgresEx *PostgresExtractor) Exec(
return rowsRead, nil
}
func (postgresEx *PostgresExtractor) Exec(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
chErrorsOut chan<- custom_errors.ExtractorError,
chJobErrorsOut chan<- custom_errors.JobError,
wgActivePartitions *sync.WaitGroup,
rowsRead *int64,
) {
}

View File

@@ -74,10 +74,6 @@ func (mssqlTr *MssqlTransformer) ProcessBatch(
}
}
if rowValues == nil {
continue
}
for _, task := range transformationPlan {
val := rowValues[task.Index]
if val == nil {

View File

@@ -10,7 +10,7 @@ import (
)
type Extractor interface {
Exec(
ProcessPartition(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -18,7 +18,20 @@ type Extractor interface {
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error)
) (int, error)
Exec(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
chErrorsOut chan<- custom_errors.ExtractorError,
chJobErrorsOut chan<- custom_errors.JobError,
wgActivePartitions *sync.WaitGroup,
rowsRead *int64,
)
}
type TransformerFunc func(any) (any, error)

View File

@@ -1,6 +1,10 @@
package models
import "github.com/google/uuid"
import (
"time"
"github.com/google/uuid"
)
type UnknownRowValues = []any
@@ -25,3 +29,13 @@ type Partition struct {
HasRange bool
RetryCounter int
}
type JobResult struct {
JobName string
StartTime time.Time
Duration time.Duration
RowsRead int64
RowsLoaded int64
RowsFailed int64
Error error
}

View File

@@ -0,0 +1,58 @@
package main
import (
"context"
"errors"
"fmt"
"net/http"
"strconv"
"github.com/cenkalti/backoff/v5"
)
func ExampleRetry() {
// Define an operation function that returns a value and an error.
// The value can be any type.
// We'll pass this operation to Retry function.
operation := func() (string, error) {
// An example request that may fail.
resp, err := http.Get("http://httpbin.org/get")
if err != nil {
return "", err
}
defer resp.Body.Close()
// If we are being rate limited, return a RetryAfter to specify how long to wait.
// This will also reset the backoff policy.
if resp.StatusCode == 429 {
seconds, err := strconv.ParseInt(resp.Header.Get("Retry-After"), 10, 64)
if err == nil {
return "", backoff.RetryAfter(int(seconds))
}
}
// In case of non-retriable error, return Permanent error to stop retrying.
// For this HTTP example, client errors are non-retriable.
if resp.StatusCode >= 400 && resp.StatusCode < 500 {
return "", backoff.Permanent(errors.New("bad request"))
}
// Return successful response.
return "hello", nil
}
result, err := backoff.Retry(context.TODO(), operation, backoff.WithBackOff(backoff.NewExponentialBackOff()))
if err != nil {
fmt.Println("Error:", err)
return
}
// Operation is successful after retries.
fmt.Println(result)
// Output: hello
}
func main() {
ExampleRetry()
}