1 Commits

Author SHA1 Message Date
DiegoAlessandroMotta
1c3db39b21 update extractor interface 2026-04-16 23:49:23 -05:00
25 changed files with 382 additions and 653 deletions

View File

@@ -1,24 +0,0 @@
# Skill Registry — go-migrate
Generated: 2026-04-21
## Compact Rules
### Go conventions
- Use existing error wrapping pattern: `fmt.Errorf("context: %w", err)`
- Channel-based pipeline — keep goroutine lifecycle clean (close channels in correct order)
- No comments unless non-obvious WHY; no docstrings
- Prefer named returns only when it aids clarity in short functions
- Use `strings.EqualFold` for case-insensitive column name comparison
### Project conventions
- Config structs live in `internal/app/config/`
- ETL interfaces live in `internal/app/etl/types.go`
- Transformer implementations in `internal/app/etl/transformers/`
- Azure operations via `internal/app/azure/main.go`
- Per-job transformer creation (not shared) when job has storage config
## User Skills
| Trigger | Skill |
|---------|-------|
| sdd-* | SDD workflow skills |

View File

@@ -1,12 +1,2 @@
SOURCE_DB_URL=sqlserver://sa:password@localhost:1433?database=master&packet+size=32767&loc=UTC
TARGET_DB_URL=postgresql://postgres:password@localhost:5432/db
LOG_LEVEL=INFO
AZ_STORAGE_ENABLED=false
AZ_ACCOUNT_NAME=
AZ_CONTAINER=
AZ_ACCOUNT_KEY=
AZ_USE_HTTPS=true
AZ_SERVICE_URL=
AZ_PREFIX=
PG_FROM_DB_URL=postgresql://postgres:password@localhost:5432/db
PG_TO_DB_URL=postgresql://postgres:password@localhost:5432/db

2
.gitignore vendored
View File

@@ -27,5 +27,5 @@ go.work.sum
# Editor/IDE
# .idea/
.vscode/
# .vscode/
.temp

77
cmd/go_migrate/connect.go Normal file
View File

@@ -0,0 +1,77 @@
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

@@ -3,7 +3,6 @@ package main
import (
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
log "github.com/sirupsen/logrus"
)
@@ -14,13 +13,5 @@ func configureLog() {
DisableSorting: false,
PadLevelText: true,
})
logLevelEnv := config.App.LogLevel
logLevel, err := log.ParseLevel(logLevelEnv)
if err != nil {
log.Warnf("Nivel de log inválido '%s', usando INFO por defecto", logLevelEnv)
logLevel = log.InfoLevel
}
log.SetLevel(logLevel)
log.SetLevel(log.DebugLevel)
}

View File

@@ -5,13 +5,12 @@ import (
"sync"
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/azure"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
dbwrapper "git.ksdemosapps.com/kylesoda/go-migrate/internal/app/db-wrapper"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/db-wrapper"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/extractors"
"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/models"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/etl/transformers"
log "github.com/sirupsen/logrus"
"golang.org/x/sync/errgroup"
)
@@ -24,7 +23,7 @@ func main() {
log.Fatalf("error leyendo configuracion: %v", err)
}
// log.Debugf("Config: %+v", migrationConfig)
log.Debugf("Config: %+v", migrationConfig)
startTime := time.Now()
@@ -96,10 +95,10 @@ func processMigrationJobs(
targetDb dbwrapper.DbWrapper,
jobs []config.Job,
maxParallelWorkers int,
) []models.JobResult {
) []JobResult {
if len(jobs) == 0 {
log.Info("No migration jobs configured")
return []models.JobResult{}
return []JobResult{}
}
if maxParallelWorkers <= 0 {
@@ -112,23 +111,15 @@ func processMigrationJobs(
log.Infof("Starting migration with %d parallel worker(s)", maxParallelWorkers)
chJobResults := make(chan models.JobResult, len(jobs))
chJobResults := make(chan JobResult, len(jobs))
chJobs := make(chan config.Job, len(jobs))
var wgJobs sync.WaitGroup
sourceTableAnalyzer := table_analyzers.NewMssqlTableAnalyzer(sourceDb)
targetTableAnalyzer := table_analyzers.NewPostgresTableAnalyzer(targetDb)
extractor := extractors.NewMssqlExtractor(sourceDb)
loader := loaders.NewGenericLoader(targetDb)
var azureClient *azure.Client
if config.App.AzureStorage.Enabled {
var err error
azureClient, err = azure.NewClient(config.App.AzureStorage)
if err != nil {
log.Fatalf("Failed to create Azure storage client: %v", err)
}
}
transformer := transformers.NewMssqlTransformer()
loader := loaders.NewPostgresLoader(targetDb)
for i := range maxParallelWorkers {
wgJobs.Go(func() {
@@ -140,10 +131,9 @@ func processMigrationJobs(
sourceTableAnalyzer,
targetTableAnalyzer,
extractor,
azureClient,
transformer,
loader,
job,
targetDb.GetDialect(),
)
chJobResults <- res
@@ -161,7 +151,7 @@ func processMigrationJobs(
close(chJobResults)
}()
var finalResults []models.JobResult
var finalResults []JobResult
for res := range chJobResults {
finalResults = append(finalResults, res)
}

13
cmd/go_migrate/metrics.go Normal file
View File

@@ -0,0 +1,13 @@
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

@@ -7,49 +7,30 @@ import (
"sync/atomic"
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/azure"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"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/etl/transformers"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/models"
log "github.com/sirupsen/logrus"
"golang.org/x/sync/errgroup"
)
func buildTruncateQuery(targetDbType, schema, table, truncateMethod string) string {
if truncateMethod == "DELETE" {
if targetDbType == "postgres" {
return fmt.Sprintf(`DELETE FROM "%s"."%s"`, schema, table)
}
return fmt.Sprintf(`DELETE FROM [%s].[%s]`, schema, table)
}
if targetDbType == "postgres" {
return fmt.Sprintf(`TRUNCATE TABLE "%s"."%s"`, schema, table)
}
return fmt.Sprintf(`TRUNCATE TABLE [%s].[%s]`, schema, table)
}
func processMigrationJob(
ctx context.Context,
targetDbWrapper dbwrapper.DbWrapper,
sourceTableAnalyzer etl.TableAnalyzer,
targetTableAnalyzer etl.TableAnalyzer,
extractor etl.Extractor,
azureClient *azure.Client,
transformer etl.Transformer,
loader etl.Loader,
job config.Job,
targetDbType string,
) models.JobResult {
transformer := transformers.NewMssqlTransformer(job.ToStorage, job.SourceTable, azureClient)
) JobResult {
localCtx, cancel := context.WithCancel(ctx)
defer cancel()
result := models.JobResult{
result := JobResult{
JobName: job.Name,
StartTime: time.Now(),
}
@@ -85,13 +66,7 @@ func processMigrationJob(
return result
}
preSqlQueries := job.TargetTable.PreSQL
if job.TruncateTarget {
truncateQuery := buildTruncateQuery(targetDbType, job.TargetTable.Schema, job.TargetTable.Table, job.TruncateMethod)
preSqlQueries = append([]string{truncateQuery}, job.TargetTable.PreSQL...)
}
for _, query := range preSqlQueries {
for _, query := range job.PreSQL {
if _, err := targetDbWrapper.Exec(localCtx, query); err != nil {
result.Error = err
return result
@@ -104,7 +79,6 @@ func processMigrationJob(
job.SourceTable.TableInfo,
job.SourceTable.PrimaryKey,
job.RowsPerPartition,
job.Range,
)
if err != nil {
log.Error("Unexpected error calculating batch ranges: ", err)
@@ -155,9 +129,8 @@ func processMigrationJob(
for range maxExtractors {
wgExtractors.Go(func() {
extractors.Consume(
extractor.Consume(
localCtx,
extractor,
job.SourceTable,
sourceColTypes,
job.BatchSize,
@@ -241,7 +214,7 @@ func processMigrationJob(
cancel()
}()
for _, query := range job.TargetTable.PostSQL {
for _, query := range job.PostSQL {
if _, err := targetDbWrapper.Exec(localCtx, query); err != nil {
result.Error = err
return result

View File

@@ -30,6 +30,7 @@ jobs:
table: MANZANA
pre_sql:
- 'SELECT 1'
# - 'TRUNCATE TABLE "Cartografia"."MANZANA"'
range:
min: 1000000
max: 2000000
@@ -47,28 +48,6 @@ jobs:
table: PUERTO
pre_sql:
- 'SELECT 1'
# - 'TRUNCATE TABLE "Red"."PUERTO"'
post_sql:
- "SELECT 1"
- name: infraestructura_site_holder__attach
source:
schema: Infraestructura
table: SITE_HOLDER__ATTACH
primary_key: GDB_ARCHIVE_OID
target:
schema: Infraestructura
table: SITE_HOLDER__ATTACH
to_storage:
columns:
- source: DATA
target: FILE_URL
mode: REFERENCE_ONLY
max_extractors: 8
max_loaders: 4
queue_size: 32
batch_size: 1
retry:
attempts: 5
base_delay_ms: 1000
max_delay_ms: 15000
max_jitter_ms: 500

12
go.mod
View File

@@ -1,13 +1,12 @@
module git.ksdemosapps.com/kylesoda/go-migrate
go 1.26
go 1.25.7
require (
github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.4
github.com/gaspardle/go-mssqlclrgeo v0.0.0-20160129143314-97ceabf987a4
github.com/google/uuid v1.6.0
github.com/ilyakaznacheev/cleanenv v1.5.0
github.com/jackc/pgx/v5 v5.9.1
github.com/joho/godotenv v1.5.1
github.com/microsoft/go-mssqldb v1.9.8
github.com/sirupsen/logrus v1.9.4
github.com/twpayne/go-geom v1.6.1
@@ -16,20 +15,15 @@ require (
)
require (
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 // indirect
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 // indirect
github.com/BurntSushi/toml v1.6.0 // 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
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
github.com/jackc/puddle/v2 v2.2.2 // indirect
github.com/joho/godotenv v1.5.1 // indirect
github.com/kr/text v0.2.0 // indirect
github.com/rogpeppe/go-internal v1.14.1 // indirect
github.com/shopspring/decimal v1.4.0 // indirect
golang.org/x/crypto v0.48.0 // indirect
golang.org/x/net v0.51.0 // indirect
golang.org/x/sys v0.41.0 // indirect
golang.org/x/text v0.34.0 // indirect
olympos.io/encoding/edn v0.0.0-20201019073823-d3554ca0b0a3 // indirect
)

16
go.sum
View File

@@ -4,25 +4,19 @@ github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1 h1:Hk5QBxZQC1jb2Fwj6mpz
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1/go.mod h1:IYus9qsFobWIc2YVwe/WPjcnyCkPKtnHAqUYeebc8z0=
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 h1:9iefClla7iYpfYWdzPCRDozdmndjTm8DXdpCzPajMgA=
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2/go.mod h1:XtLgD3ZD34DAaVIIAyG3objl5DynM3CQ/vMcbBNJZGI=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/storage/armstorage v1.8.1 h1:/Zt+cDPnpC3OVDm/JKLOs7M2DKmLRIIp3XIx9pHHiig=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/storage/armstorage v1.8.1/go.mod h1:Ng3urmn6dYe8gnbCMoHHVl5APYz2txho3koEkV2o2HA=
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azkeys v1.4.0 h1:E4MgwLBGeVB5f2MdcIVD3ELVAWpr+WD6MUe1i+tM/PA=
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azkeys v1.4.0/go.mod h1:Y2b/1clN4zsAoUd/pgNAQHjLDnTis/6ROkUfyob6psM=
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/internal v1.2.0 h1:nCYfgcSyHZXJI8J0IWE5MsCGlb2xp9fJiXyxWgmOFg4=
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/internal v1.2.0/go.mod h1:ucUjca2JtSZboY8IoUqyQyuuXvwbMBVwFOm0vdQPNhA=
github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.4 h1:jWQK1GI+LeGGUKBADtcH2rRqPxYB1Ljwms5gFA2LqrM=
github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.4/go.mod h1:8mwH4klAm9DUgR2EEHyEEAQlRDvLPyg5fQry3y+cDew=
github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 h1:XRzhVemXdgvJqCH0sFfrBUTnUJSBrBf7++ypk+twtRs=
github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0/go.mod h1:HKpQxkWaGLJ+D/5H8QRpyQXA1eKjxkFlOMwck5+33Jk=
github.com/BurntSushi/toml v1.2.1/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
github.com/BurntSushi/toml v1.6.0 h1:dRaEfpa2VI55EwlIW72hMRHdWouJeRF7TPYhI+AUQjk=
github.com/BurntSushi/toml v1.6.0/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
github.com/DATA-DOG/go-sqlmock v1.5.2 h1:OcvFkGmslmlZibjAjaHm3L//6LiuBgolP7OputlJIzU=
github.com/DATA-DOG/go-sqlmock v1.5.2/go.mod h1:88MAG/4G7SMwSE3CeA0ZKzrT5CiOU3OJ+JlNzwDqpNU=
github.com/alecthomas/assert/v2 v2.10.0 h1:jjRCHsj6hBJhkmhznrCzoNpbA3zqy0fYiUcYZP/GkPY=
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/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=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -38,8 +32,6 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
github.com/ilyakaznacheev/cleanenv v1.5.0 h1:0VNZXggJE2OYdXE87bfSSwGxeiGt9moSR2lOrsHHvr4=
github.com/ilyakaznacheev/cleanenv v1.5.0/go.mod h1:a5aDzaJrLCQZsazHol1w8InnDcOX0OColm64SlIi6gk=
github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 h1:iCEnooe7UlwOQYpKFhBabPMi4aNAfoODPEFNiAnClxo=
@@ -50,8 +42,8 @@ github.com/jackc/puddle/v2 v2.2.2 h1:PR8nw+E/1w0GLuRFSmiioY6UooMp6KJv0/61nB7icHo
github.com/jackc/puddle/v2 v2.2.2/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4=
github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
@@ -91,5 +83,3 @@ gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EV
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
olympos.io/encoding/edn v0.0.0-20201019073823-d3554ca0b0a3 h1:slmdOY3vp8a7KQbHkL+FLbvbkgMqmXojpFUO/jENuqQ=
olympos.io/encoding/edn v0.0.0-20201019073823-d3554ca0b0a3/go.mod h1:oVgVk4OWVDi43qWBEyGhXgYxt7+ED4iYNpTngSLX2Iw=

View File

@@ -1,87 +0,0 @@
package azure
import (
"context"
"errors"
"fmt"
"net/url"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"github.com/Azure/azure-sdk-for-go/sdk/storage/azblob"
)
var (
ErrInvalidConnectionString = errors.New("invalid connection string")
ErrContainerNotFound = errors.New("container not found")
ErrBlobNotFound = errors.New("blob not found")
ErrInvalidInput = errors.New("invalid input parameters")
)
type Client struct {
client *azblob.Client
azureStorageConfig config.AzureStorageConfig
}
func NewClient(azureStorageConfig config.AzureStorageConfig) (*Client, error) {
protocol := "https"
if !azureStorageConfig.UseHTTPS {
protocol = "http"
}
blobEndpoint, _ := url.JoinPath(azureStorageConfig.ServiceURL, azureStorageConfig.AccountName)
connStr := fmt.Sprintf("DefaultEndpointsProtocol=%s;AccountName=%s;AccountKey=%s;BlobEndpoint=%s;",
protocol, azureStorageConfig.AccountName, azureStorageConfig.AccountKey, blobEndpoint)
client, err := azblob.NewClientFromConnectionString(connStr, nil)
if err != nil {
return nil, fmt.Errorf("creating azure storage client: %w", err)
}
return &Client{
client: client,
azureStorageConfig: azureStorageConfig,
}, nil
}
func (c *Client) CreateContainer(ctx context.Context, containerName string) error {
if containerName == "" {
return ErrInvalidInput
}
_, err := c.client.CreateContainer(ctx, containerName, nil)
if err != nil {
return fmt.Errorf("creating container %s: %w", containerName, err)
}
return nil
}
func (c *Client) UploadBuffer(ctx context.Context, containerName, blobPath string, buffer []byte) error {
if containerName == "" || blobPath == "" || buffer == nil {
return ErrInvalidInput
}
_, err := c.client.UploadBuffer(ctx, containerName, blobPath, buffer, nil)
if err != nil {
return fmt.Errorf("uploading blob %s: %w", blobPath, err)
}
return nil
}
func (c *Client) UploadAndGetURL(ctx context.Context, blobPath string, buffer []byte) (string, error) {
if blobPath == "" || buffer == nil {
return "", ErrInvalidInput
}
fullPath := blobPath
if c.azureStorageConfig.Prefix != "" {
fullPath, _ = url.JoinPath(c.azureStorageConfig.Prefix, blobPath)
}
if err := c.UploadBuffer(ctx, c.azureStorageConfig.Container, fullPath, buffer); err != nil {
return "", err
}
blobEndpoint, _ := url.JoinPath(c.azureStorageConfig.ServiceURL, c.azureStorageConfig.AccountName)
blobURL, _ := url.JoinPath(blobEndpoint, c.azureStorageConfig.Container, fullPath)
return blobURL, nil
}

View File

@@ -1,41 +1,41 @@
package config
import (
"github.com/ilyakaznacheev/cleanenv"
"os"
"github.com/joho/godotenv"
log "github.com/sirupsen/logrus"
)
type AzureStorageConfig struct {
AccountName string `env:"AZ_ACCOUNT_NAME"`
Container string `env:"AZ_CONTAINER"`
AccountKey string `env:"AZ_ACCOUNT_KEY"`
UseHTTPS bool `env:"AZ_USE_HTTPS" env-default:"true"`
ServiceURL string `env:"AZ_SERVICE_URL"`
Prefix string `env:"AZ_PREFIX"`
Enabled bool `env:"AZ_STORAGE_ENABLED"`
type appConfig struct {
SourceDbUrl string
TargetDbUrl string
}
type appConfig struct {
SourceDbUrl string `env:"SOURCE_DB_URL" env-required:"true"`
TargetDbUrl string `env:"TARGET_DB_URL" env-required:"true"`
LogLevel string `env:"LOG_LEVEL" env-default:"INFO"`
AzureStorage AzureStorageConfig
func loadEnv() {
err := godotenv.Load()
if err != nil {
log.Warn("Warning: could not load .env file")
}
}
func getAppConfig() appConfig {
var cfg appConfig
loadEnv()
err := cleanenv.ReadConfig(".env", &cfg)
if err != nil {
log.Warn("Could not load .env file")
sourceDbUrl := os.Getenv("SOURCE_DB_URL")
if sourceDbUrl == "" {
log.Fatal("SOURCE_DB_URL environment variable not set")
}
err = cleanenv.ReadEnv(&cfg)
if err != nil {
log.Fatalf("Error al cargar variables: %v", err)
targetDbUrl := os.Getenv("TARGET_DB_URL")
if targetDbUrl == "" {
log.Fatal("TARGET_DB_URL environment variable not set")
}
return cfg
return appConfig{
SourceDbUrl: sourceDbUrl,
TargetDbUrl: targetDbUrl,
}
}
var App appConfig = getAppConfig()

View File

@@ -14,16 +14,6 @@ type RetryConfig struct {
MaxJitterMs int `yaml:"max_jitter_ms"`
}
type ToStorageColumnConfig struct {
Source string `yaml:"source"`
Target string `yaml:"target"`
Mode string `yaml:"mode"`
}
type ToStorageConfig struct {
Columns []ToStorageColumnConfig `yaml:"columns"`
}
type JobConfig struct {
MaxExtractors int `yaml:"max_extractors"`
MaxLoaders int `yaml:"max_loaders"`
@@ -36,7 +26,6 @@ type JobConfig struct {
MaxChunkErrors int `yaml:"max_chunk_errors"`
Retry RetryConfig `yaml:"retry"`
RowsPerPartition int64
ToStorage ToStorageConfig `yaml:"to_storage"`
}
type TableInfo struct {
@@ -44,31 +33,29 @@ type TableInfo struct {
Table string `yaml:"table"`
}
type TargetTableInfo struct {
TableInfo `yaml:",inline"`
}
type SourceTableInfo struct {
TableInfo `yaml:",inline"`
PrimaryKey string `yaml:"primary_key"`
}
type TargetTableInfo struct {
TableInfo `yaml:",inline"`
PreSQL []string `yaml:"pre_sql"`
PostSQL []string `yaml:"post_sql"`
}
type RangeConfig struct {
Min int64 `yaml:"min"`
Max int64 `yaml:"max"`
IsMinInclusive bool `yaml:"is_min_inclusive"`
IsMaxInclusive bool `yaml:"is_max_inclusive"`
}
type Job struct {
Name string `yaml:"name"`
Enabled bool `yaml:"enabled"`
SourceTable SourceTableInfo `yaml:"source"`
TargetTable TargetTableInfo `yaml:"target"`
PreSQL []string `yaml:"pre_sql"`
PostSQL []string `yaml:"post_sql"`
JobConfig `yaml:",inline"`
Range RangeConfig `yaml:"range"`
Range struct {
Min int64 `yaml:"min"`
Max int64 `yaml:"max"`
IsMinInclusive bool `yaml:"is_min_inclusive"`
IsMaxInclusive bool `yaml:"is_max_inclusive"`
}
}
type MigrationConfig struct {

View File

@@ -1,101 +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.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 := extractor.Exec(
ctx,
tableInfo,
columns,
batchSize,
partition,
indexPrimaryKey,
chBatchesOut,
)
if rowsReadResult > 0 {
atomic.AddInt64(rowsRead, int64(rowsReadResult))
}
if err != nil {
if exError, ok := errors.AsType[*custom_errors.ExtractorError](err); ok {
select {
case <-ctx.Done():
return
case chErrorsOut <- *exError:
}
} else if jobError, ok := errors.AsType[*custom_errors.JobError](err); ok {
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

@@ -5,7 +5,11 @@ import (
"database/sql"
"errors"
"fmt"
"slices"
"strings"
"sync"
"sync/atomic"
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/convert"
@@ -29,9 +33,6 @@ func buildExtractQueryMssql(
columns []models.ColumnType,
includeRange bool,
isMinInclusive bool,
isMaxInclusive bool,
hasMin bool,
hasMax bool,
) string {
var sbQuery strings.Builder
@@ -55,32 +56,15 @@ func buildExtractQueryMssql(
fmt.Fprintf(&sbQuery, " FROM [%s].[%s]", tableInfo.Schema, tableInfo.Table)
if includeRange && (hasMin || hasMax) {
sbQuery.WriteString(" WHERE ")
if hasMin {
fmt.Fprintf(&sbQuery, "[%s]", tableInfo.PrimaryKey)
if includeRange {
fmt.Fprintf(&sbQuery, " WHERE [%s]", tableInfo.PrimaryKey)
if isMinInclusive {
sbQuery.WriteString(" >=")
} else {
sbQuery.WriteString(" >")
}
sbQuery.WriteString(" @min")
}
if hasMin && hasMax {
sbQuery.WriteString(" AND ")
}
if hasMax {
fmt.Fprintf(&sbQuery, "[%s]", tableInfo.PrimaryKey)
if isMaxInclusive {
sbQuery.WriteString(" <=")
} else {
sbQuery.WriteString(" <")
}
sbQuery.WriteString(" @max")
}
fmt.Fprintf(&sbQuery, " @min AND [%s] <= @max", tableInfo.PrimaryKey)
}
fmt.Fprintf(&sbQuery, " ORDER BY [%s] ASC", tableInfo.PrimaryKey)
@@ -116,7 +100,7 @@ func errorFromLastRow(
}
}
func (mssqlEx *MssqlExtractor) Exec(
func (mssqlEx *MssqlExtractor) Extract(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -124,20 +108,18 @@ func (mssqlEx *MssqlExtractor) Exec(
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int, error) {
hasMin := partition.HasRange && partition.Range.Min > 0
hasMax := partition.HasRange && partition.Range.Max > 0
query := buildExtractQueryMssql(tableInfo, columns, partition.HasRange, partition.Range.IsMinInclusive, partition.Range.IsMaxInclusive, hasMin, hasMax)
) (int64, error) {
query := buildExtractQueryMssql(tableInfo, columns, partition.HasRange, partition.Range.IsMinInclusive)
var queryArgs []any
if hasMin {
queryArgs = append(queryArgs, sql.Named("min", partition.Range.Min))
}
if hasMax {
queryArgs = append(queryArgs, sql.Named("max", partition.Range.Max))
if partition.HasRange {
queryArgs = append(queryArgs,
sql.Named("min", partition.Range.Min),
sql.Named("max", partition.Range.Max),
)
}
rowsRead := 0
var rowsRead int64 = 0
rows, err := mssqlEx.db.Query(ctx, query, queryArgs...)
if err != nil {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
@@ -207,3 +189,136 @@ func (mssqlEx *MssqlExtractor) Exec(
return rowsRead, nil
}
func (mssqlEx *MssqlExtractor) ExtractWithRetries(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error) {
var totalRowsRead int64
var fatalErr error
delay := time.Duration(time.Second * 1)
currentParitition := partition
for fatalErr != nil || currentParitition.RetryCounter < 3 {
currentParitition.RetryCounter++
rowsRead, err := mssqlEx.Extract(
ctx,
tableInfo,
columns,
batchSize,
currentParitition,
indexPrimaryKey,
chBatchesOut,
)
if rowsRead > 0 {
totalRowsRead += int64(rowsRead)
}
if err != nil {
var exError *custom_errors.ExtractorError
if errors.As(err, &exError) {
if exError.HasLastId {
currentParitition.ParentId = exError.Partition.Id
currentParitition.Id = uuid.New()
currentParitition.Range.Min = exError.LastId
currentParitition.Range.IsMinInclusive = false
}
time.Sleep(delay)
} else {
fatalErr = err
}
continue
}
break
}
return totalRowsRead, fatalErr
}
func (mssqlEx *MssqlExtractor) Consume(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
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.ExtractWithRetries(
ctx,
tableInfo,
columns,
batchSize,
partition,
indexPrimaryKey,
chBatchesOut,
)
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 chJobErrorsOut <- *jobError:
}
} else {
select {
case <-ctx.Done():
return
case chJobErrorsOut <- custom_errors.JobError{ShouldCancelJob: false, Msg: err.Error(), Prev: err}:
}
}
continue
}
wgActivePartitions.Done()
}
}
}

View File

@@ -2,8 +2,10 @@ package extractors
import (
"context"
"errors"
"fmt"
"strings"
"sync"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/custom_errors"
@@ -21,15 +23,7 @@ func NewPostgresExtractor(db dbwrapper.DbWrapper) etl.Extractor {
return &PostgresExtractor{db: db}
}
func buildExtractQueryPostgres(
sourceDbInfo config.SourceTableInfo,
columns []models.ColumnType,
includeRange bool,
isMinInclusive bool,
isMaxInclusive bool,
hasMin bool,
hasMax bool,
) string {
func buildExtractQueryPostgres(sourceDbInfo config.SourceTableInfo, columns []models.ColumnType) string {
var sbColumns strings.Builder
if len(columns) == 0 {
@@ -54,44 +48,10 @@ func buildExtractQueryPostgres(
}
}
query := fmt.Sprintf(`SELECT %s FROM "%s"."%s"`, sbColumns.String(), sourceDbInfo.Schema, sourceDbInfo.Table)
if includeRange && (hasMin || hasMax) {
query += " WHERE "
paramIdx := 1
if hasMin {
query += fmt.Sprintf(`"%s"`, sourceDbInfo.PrimaryKey)
if isMinInclusive {
query += " >="
} else {
query += " >"
}
query += fmt.Sprintf(" $%d", paramIdx)
paramIdx++
}
if hasMin && hasMax {
query += " AND "
}
if hasMax {
query += fmt.Sprintf(`"%s"`, sourceDbInfo.PrimaryKey)
if isMaxInclusive {
query += " <="
} else {
query += " <"
}
query += fmt.Sprintf(" $%d", paramIdx)
}
}
query += fmt.Sprintf(` ORDER BY "%s" ASC`, sourceDbInfo.PrimaryKey)
return query
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) Extract(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -100,20 +60,14 @@ func (postgresEx *PostgresExtractor) Exec(
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int, error) {
hasMin := partition.HasRange && partition.Range.Min > 0
hasMax := partition.HasRange && partition.Range.Max > 0
query := buildExtractQueryPostgres(tableInfo, columns, partition.HasRange, partition.Range.IsMinInclusive, partition.Range.IsMaxInclusive, hasMin, hasMax)
query := buildExtractQueryPostgres(tableInfo, columns)
var queryArgs []any
if hasMin {
queryArgs = append(queryArgs, partition.Range.Min)
}
if hasMax {
queryArgs = append(queryArgs, partition.Range.Max)
if partition.HasRange {
return 0, errors.New("Batch config not yet supported")
}
rowsRead := 0
rows, err := postgresEx.db.Query(ctx, query, queryArgs...)
rows, err := postgresEx.db.Query(ctx, query)
if err != nil {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
}
@@ -124,7 +78,7 @@ func (postgresEx *PostgresExtractor) Exec(
for rows.Next() {
values, err := rows.Values()
if err != nil {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
return rowsRead, errors.New("Unexpected error reading rows from source")
}
rowsRead++
@@ -142,7 +96,7 @@ func (postgresEx *PostgresExtractor) Exec(
}
if err := rows.Err(); err != nil {
return rowsRead, &custom_errors.ExtractorError{Partition: partition, HasLastId: false, Msg: err.Error()}
return rowsRead, errors.New("Unexpected error reading rows from source")
}
if len(batchRows) > 0 {
@@ -155,3 +109,17 @@ func (postgresEx *PostgresExtractor) Exec(
return rowsRead, nil
}
func (postgresEx *PostgresExtractor) Consume(
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

@@ -15,21 +15,31 @@ import (
"github.com/jackc/pgx/v5/pgconn"
)
type GenericLoader struct {
type PostgresLoader struct {
db dbwrapper.DbWrapper
}
func NewGenericLoader(db dbwrapper.DbWrapper) etl.Loader {
return &GenericLoader{db: db}
func NewPostgresLoader(db dbwrapper.DbWrapper) etl.Loader {
return &PostgresLoader{db: db}
}
func (gl *GenericLoader) ProcessBatch(
func mapSlice[T any, V any](input []T, mapper func(T) V) []V {
result := make([]V, len(input))
for i, v := range input {
result[i] = mapper(v)
}
return result
}
func (postgresLd *PostgresLoader) ProcessBatch(
ctx context.Context,
tableInfo config.TargetTableInfo,
colNames []string,
batch models.Batch,
) (int, error) {
_, err := gl.db.SaveMassive(
_, err := postgresLd.db.SaveMassive(
ctx,
tableInfo.Schema,
tableInfo.Table,
@@ -55,7 +65,7 @@ func (gl *GenericLoader) ProcessBatch(
return len(batch.Rows), nil
}
func (gl *GenericLoader) Exec(
func (postgresLd *PostgresLoader) Exec(
ctx context.Context,
tableInfo config.TargetTableInfo,
columns []models.ColumnType,
@@ -82,7 +92,7 @@ func (gl *GenericLoader) Exec(
return
}
processedRows, err := gl.ProcessBatch(ctx, tableInfo, colNames, batch)
processedRows, err := postgresLd.ProcessBatch(ctx, tableInfo, colNames, batch)
if err != nil {
var ldError *custom_errors.LoaderError

View File

@@ -0,0 +1 @@
package loaders

View File

@@ -1,11 +0,0 @@
package loaders
func mapSlice[T any, V any](input []T, mapper func(T) V) []V {
result := make([]V, len(input))
for i, v := range input {
result[i] = mapper(v)
}
return result
}

View File

@@ -15,22 +15,7 @@ func PartitionRangeGenerator(
tableInfo config.TableInfo,
partitionColumn string,
rowsPerPartition int64,
jobRange config.RangeConfig,
) ([]models.Partition, error) {
if jobRange.Min > 0 {
return []models.Partition{{
Id: uuid.New(),
HasRange: true,
RetryCounter: 0,
Range: models.PartitionRange{
Min: jobRange.Min,
Max: jobRange.Max,
IsMinInclusive: jobRange.IsMinInclusive,
IsMaxInclusive: jobRange.IsMaxInclusive,
},
}}, nil
}
rowsCount, err := tableAnalyzer.EstimateTotalRows(ctx, tableInfo)
if err != nil {
return nil, err

View File

@@ -3,32 +3,18 @@ package transformers
import (
"context"
"errors"
"fmt"
"strings"
"sync"
"time"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/azure"
"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"
log "github.com/sirupsen/logrus"
)
type MssqlTransformer struct {
toStorage config.ToStorageConfig
sourceTable config.SourceTableInfo
azureClient *azure.Client
}
type MssqlTransformer struct{}
func NewMssqlTransformer(toStorage config.ToStorageConfig, sourceTable config.SourceTableInfo, azureClient *azure.Client) etl.Transformer {
return &MssqlTransformer{
toStorage: toStorage,
sourceTable: sourceTable,
azureClient: azureClient,
}
func NewMssqlTransformer() etl.Transformer {
return &MssqlTransformer{}
}
func computeTransformationPlan(columns []models.ColumnType) []etl.ColumnTransformPlan {
@@ -74,65 +60,6 @@ func computeTransformationPlan(columns []models.ColumnType) []etl.ColumnTransfor
return plan
}
func computeStorageTransformationPlan(
ctx context.Context,
azureClient *azure.Client,
toStorage config.ToStorageConfig,
sourceColumns []models.ColumnType,
sourceTable config.SourceTableInfo,
) []etl.ColumnTransformPlan {
if azureClient == nil || len(toStorage.Columns) == 0 {
return nil
}
colIndex := make(map[string]int, len(sourceColumns))
for i, col := range sourceColumns {
colIndex[strings.ToUpper(col.Name())] = i
}
var plan []etl.ColumnTransformPlan
for _, storageCol := range toStorage.Columns {
if storageCol.Mode != "REFERENCE_ONLY" {
log.Warnf("to_storage: unsupported mode %q for column %s — skipping", storageCol.Mode, storageCol.Source)
continue
}
idx, ok := colIndex[strings.ToUpper(storageCol.Source)]
if !ok {
log.Warnf("to_storage: source column %q not found in source schema — skipping", storageCol.Source)
continue
}
sourceColName := storageCol.Source
schema := sourceTable.Schema
table := sourceTable.Table
plan = append(plan, etl.ColumnTransformPlan{
Index: idx,
Fn: func(v any) (any, error) {
if v == nil {
return nil, nil
}
b, ok := v.([]byte)
if !ok {
log.Warnf("to_storage: expected []byte for %s.%s.%s, got %T — passing through",
schema, table, sourceColName, v)
return v, nil
}
start := time.Now()
blobPath := fmt.Sprintf("%s/%s/%s", schema, table, uuid.New().String())
blobURL, err := azureClient.UploadAndGetURL(ctx, blobPath, b)
if err != nil {
return nil, fmt.Errorf("uploading %s.%s.%s: %w", schema, table, sourceColName, err)
}
log.Debugf(`Succesfully uploaded "%s", (%vms)`, blobURL, time.Since(start).Milliseconds())
return blobURL, nil
},
})
}
return plan
}
const processBatchCtxCheck = 4096
func (mssqlTr *MssqlTransformer) ProcessBatch(
@@ -173,8 +100,6 @@ func (mssqlTr *MssqlTransformer) Exec(
wgActiveBatches *sync.WaitGroup,
) {
transformationPlan := computeTransformationPlan(columns)
storagePlan := computeStorageTransformationPlan(ctx, mssqlTr.azureClient, mssqlTr.toStorage, columns, mssqlTr.sourceTable)
transformationPlan = append(transformationPlan, storagePlan...)
for {
if ctx.Err() != nil {

View File

@@ -10,7 +10,7 @@ import (
)
type Extractor interface {
Exec(
Extract(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
@@ -18,7 +18,29 @@ type Extractor interface {
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int, error)
) (int64, error)
ExtractWithRetries(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
partition models.Partition,
indexPrimaryKey int,
chBatchesOut chan<- models.Batch,
) (int64, error)
Consume(
ctx context.Context,
tableInfo config.SourceTableInfo,
columns []models.ColumnType,
batchSize int,
chPartitionsIn <-chan models.Partition,
chBatchesOut chan<- models.Batch,
chJobErrorsOut chan<- custom_errors.JobError,
wgActivePartitions *sync.WaitGroup,
rowsRead *int64,
)
}
type TransformerFunc func(any) (any, error)

View File

@@ -1,10 +1,6 @@
package models
import (
"time"
"github.com/google/uuid"
)
import "github.com/google/uuid"
type UnknownRowValues = []any
@@ -29,13 +25,3 @@ 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

@@ -1,44 +0,0 @@
package main
import (
"context"
"fmt"
"log"
"math/rand"
"sync"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/azure"
"git.ksdemosapps.com/kylesoda/go-migrate/internal/app/config"
)
func main() {
cfg := config.App.AzureStorage
containerName := cfg.Container
client, err := azure.NewClient(cfg)
if err != nil {
log.Fatalf("Error creando cliente: %v", err)
}
ctx := context.Background()
var wg sync.WaitGroup
for i := 1; i <= 10; i++ {
wg.Add(1)
go func(id int) {
defer wg.Done()
blobName := fmt.Sprintf("%sarchivo-%d.txt", cfg.Prefix, id)
content := fmt.Sprintf("Contenido aleatorio: %d", rand.Intn(100000))
err := client.UploadBuffer(ctx, containerName, blobName, []byte(content))
if err != nil {
log.Printf("Fallo al subir %s: %v", blobName, err)
} else {
fmt.Printf("Subido exitosamente: %s\n", blobName)
}
}(i)
}
wg.Wait()
}