refactor: implement extractor retry logic and streamline extractor interface

This commit is contained in:
2026-04-17 00:33:49 -05:00
parent 15d1b96849
commit 46597c4ffd
6 changed files with 170 additions and 235 deletions

View File

@@ -0,0 +1,94 @@
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, int64(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}:
}
}
continue
}
}
}
}