Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support null in Airbyte schema column type #123

Merged
merged 5 commits into from
Feb 20, 2025
Merged

Support null in Airbyte schema column type #123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
dc321a9
Allow multiple data types, mostly to support nullable data types
notfelineit Feb 20, 2025
ae54e96
Update tests
notfelineit Feb 20, 2025
a669290
Update tests to expect type as slice of strings
notfelineit Feb 20, 2025
47c31c3
Add nullable test
notfelineit Feb 20, 2025
7c823df
Pass IsNullable
notfelineit Feb 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cmd/airbyte-source/read.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ func ReadCommand(ch *Helper) *cobra.Command {

catalog, err := readCatalog(readSourceCatalogPath)
if err != nil {
ch.Logger.Error("Unable to read catalog")
ch.Logger.Error(fmt.Sprintf("Unable to read catalog: %+v", err))
os.Exit(1)
}

Expand Down
4 changes: 2 additions & 2 deletions cmd/airbyte-source/read_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ func TestRead_StartingGtidsAndState(t *testing.T) {
Type: "object",
Properties: map[string]internal.PropertyType{
"id": {
Type: "number",
Type: []string{"number"},
AirbyteType: "integer",
},
},
Expand All @@ -55,7 +55,7 @@ func TestRead_StartingGtidsAndState(t *testing.T) {
Type: "object",
Properties: map[string]internal.PropertyType{
"id": {
Type: "number",
Type: []string{"number"},
AirbyteType: "integer",
},
},
Expand Down
27 changes: 18 additions & 9 deletions cmd/internal/planetscale_edge_database.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,28 +132,37 @@ func (p PlanetScaleEdgeDatabase) getStreamForTable(ctx context.Context, psc Plan
}

// Convert columnType to Airbyte type.
func getJsonSchemaType(mysqlType string, treatTinyIntAsBoolean bool) PropertyType {
func getJsonSchemaType(mysqlType string, treatTinyIntAsBoolean bool, nullable string) PropertyType {
// Support custom airbyte types documented here :
// https://docs.airbyte.com/understanding-airbyte/supported-data-types/#the-types
var propertyType PropertyType

switch {
case strings.HasPrefix(mysqlType, "tinyint(1)"):
if treatTinyIntAsBoolean {
return PropertyType{Type: "boolean"}
propertyType = PropertyType{Type: []string{"boolean"}}
} else {
propertyType = PropertyType{Type: []string{"number"}, AirbyteType: "integer"}
}
return PropertyType{Type: "number", AirbyteType: "integer"}
case strings.HasPrefix(mysqlType, "int"), strings.HasPrefix(mysqlType, "smallint"), strings.HasPrefix(mysqlType, "mediumint"), strings.HasPrefix(mysqlType, "bigint"), strings.HasPrefix(mysqlType, "tinyint"):
return PropertyType{Type: "number", AirbyteType: "integer"}
propertyType = PropertyType{Type: []string{"number"}, AirbyteType: "integer"}
case strings.HasPrefix(mysqlType, "decimal"), strings.HasPrefix(mysqlType, "double"), strings.HasPrefix(mysqlType, "float"):
return PropertyType{Type: "number"}
propertyType = PropertyType{Type: []string{"number"}}
case strings.HasPrefix(mysqlType, "datetime"), strings.HasPrefix(mysqlType, "timestamp"):
return PropertyType{Type: "string", CustomFormat: "date-time", AirbyteType: "timestamp_without_timezone"}
propertyType = PropertyType{Type: []string{"string"}, CustomFormat: "date-time", AirbyteType: "timestamp_without_timezone"}
case strings.HasPrefix(mysqlType, "date"):
return PropertyType{Type: "string", CustomFormat: "date", AirbyteType: "date"}
propertyType = PropertyType{Type: []string{"string"}, CustomFormat: "date", AirbyteType: "date"}
case strings.HasPrefix(mysqlType, "time"):
return PropertyType{Type: "string", CustomFormat: "time", AirbyteType: "time_without_timezone"}
propertyType = PropertyType{Type: []string{"string"}, CustomFormat: "time", AirbyteType: "time_without_timezone"}
default:
return PropertyType{Type: "string"}
propertyType = PropertyType{Type: []string{"string"}}
}

if strings.ToLower(nullable) == "yes" {
propertyType.Type = append(propertyType.Type, "null")
}

return propertyType
}

func (p PlanetScaleEdgeDatabase) Close() error {
Expand Down
53 changes: 30 additions & 23 deletions cmd/internal/planetscale_edge_database_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -359,126 +359,133 @@ func TestRead_CanPickRdonlyForShardedKeyspaces(t *testing.T) {
func TestDiscover_CanPickRightAirbyteType(t *testing.T) {
var tests = []struct {
MysqlType string
JSONSchemaType string
JSONSchemaType []string
AirbyteType string
TreatTinyIntAsBoolean bool
IsNullable string
}{
{
MysqlType: "int(11)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "smallint(4)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "mediumint(8)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "tinyint",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
TreatTinyIntAsBoolean: true,
},
{
MysqlType: "tinyint(1)",
JSONSchemaType: "boolean",
JSONSchemaType: []string{"boolean"},
AirbyteType: "",
TreatTinyIntAsBoolean: true,
},
{
MysqlType: "tinyint(1) unsigned",
JSONSchemaType: "boolean",
JSONSchemaType: []string{"boolean"},
AirbyteType: "",
TreatTinyIntAsBoolean: true,
},
{
MysqlType: "tinyint(1)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
TreatTinyIntAsBoolean: false,
},
{
MysqlType: "tinyint(1) unsigned",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
TreatTinyIntAsBoolean: false,
},
{
MysqlType: "bigint(16)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "bigint unsigned",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "bigint zerofill",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "integer",
},
{
MysqlType: "datetime",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "timestamp_without_timezone",
},
{
MysqlType: "datetime(6)",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "timestamp_without_timezone",
},
{
MysqlType: "time",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "time_without_timezone",
},
{
MysqlType: "time(6)",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "time_without_timezone",
},
{
MysqlType: "date",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "date",
},
{
MysqlType: "text",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "",
},
{
MysqlType: "varchar(256)",
JSONSchemaType: "string",
JSONSchemaType: []string{"string"},
AirbyteType: "",
},
{
MysqlType: "varchar(256)",
JSONSchemaType: []string{"string", "null"},
AirbyteType: "",
IsNullable: "YES",
},
{
MysqlType: "decimal(12,5)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "",
},
{
MysqlType: "double",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "",
},
{
MysqlType: "float(30)",
JSONSchemaType: "number",
JSONSchemaType: []string{"number"},
AirbyteType: "",
},
}

for _, typeTest := range tests {

t.Run(fmt.Sprintf("mysql_type_%v", typeTest.MysqlType), func(t *testing.T) {
p := getJsonSchemaType(typeTest.MysqlType, typeTest.TreatTinyIntAsBoolean)
p := getJsonSchemaType(typeTest.MysqlType, typeTest.TreatTinyIntAsBoolean, typeTest.IsNullable)
assert.Equal(t, typeTest.AirbyteType, p.AirbyteType)
assert.Equal(t, typeTest.JSONSchemaType, p.Type)
})
Expand Down
7 changes: 4 additions & 3 deletions cmd/internal/planetscale_edge_mysql.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,7 +157,7 @@ func (p planetScaleEdgeMySQLAccess) GetTableSchema(ctx context.Context, psc Plan

columnNamesQR, err := p.db.QueryContext(
ctx,
"select column_name, column_type from information_schema.columns where table_name=? AND table_schema=?;",
"select column_name, column_type, is_nullable from information_schema.columns where table_name=? AND table_schema=?;",
tableName, psc.Database,
)
if err != nil {
Expand All @@ -168,12 +168,13 @@ func (p planetScaleEdgeMySQLAccess) GetTableSchema(ctx context.Context, psc Plan
var (
name string
columnType string
nullable string
)
if err = columnNamesQR.Scan(&name, &columnType); err != nil {
if err = columnNamesQR.Scan(&name, &columnType, &nullable); err != nil {
return properties, errors.Wrapf(err, "Unable to scan row for column names & types of table %v", tableName)
}

properties[name] = getJsonSchemaType(columnType, !psc.Options.DoNotTreatTinyIntAsBoolean)
properties[name] = getJsonSchemaType(columnType, !psc.Options.DoNotTreatTinyIntAsBoolean, nullable)
}

if err := columnNamesQR.Err(); err != nil {
Expand Down
6 changes: 3 additions & 3 deletions cmd/internal/types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,9 +54,9 @@ const (
)

type PropertyType struct {
Type string `json:"type"`
CustomFormat string `json:"format,omitempty"`
AirbyteType string `json:"airbyte_type,omitempty"`
Type []string `json:"type"`
CustomFormat string `json:"format,omitempty"`
AirbyteType string `json:"airbyte_type,omitempty"`
}

type StreamSchema struct {
Expand Down
Loading