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

[Databricks] Better handling of TOAST columns #1083

Merged
merged 4 commits into from
Dec 16, 2024
Merged

[Databricks] Better handling of TOAST columns #1083

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
de27f69
WIP.
Tang8330 Dec 15, 2024
64f85be
Escape correctly.
Tang8330 Dec 16, 2024
739d942
Update.
Tang8330 Dec 16, 2024
b0860de
Clean up.
Tang8330 Dec 16, 2024
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
9 changes: 6 additions & 3 deletions clients/databricks/dialect/dialect.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,11 +31,14 @@ func (DatabricksDialect) IsTableDoesNotExistErr(err error) bool {
}

func (d DatabricksDialect) BuildIsNotToastValueExpression(tableAlias constants.TableAlias, column columns.Column) string {
toastedValue := "%" + constants.ToastUnavailableValuePlaceholder + "%"
colName := sql.QuoteTableAliasColumn(tableAlias, column, d)
if column.KindDetails == typing.Struct {
return fmt.Sprintf("COALESCE(%s != {'key': '%s'}, true)", colName, constants.ToastUnavailableValuePlaceholder)
switch column.KindDetails {
case typing.String:
return fmt.Sprintf("COALESCE(%s NOT LIKE '%s', TRUE)", colName, toastedValue)
default:
return fmt.Sprintf("COALESCE(TO_VARCHAR(%s) NOT LIKE '%s', TRUE)", colName, toastedValue)
}
return fmt.Sprintf("COALESCE(%s != '%s', true)", colName, constants.ToastUnavailableValuePlaceholder)
}

func (DatabricksDialect) BuildDedupeTableQuery(tableID sql.TableIdentifier, primaryKeys []string) string {
Expand Down
24 changes: 24 additions & 0 deletions clients/databricks/dialect/dialect_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,30 @@ func TestDatabricksDialect_IsTableDoesNotExistErr(t *testing.T) {
}
}

func TestDatabricks_BuildIsNotToastValueExpression(t *testing.T) {
{
// Unspecified data type
assert.Equal(t,
"COALESCE(TO_VARCHAR(tbl.`bar`) NOT LIKE '%__debezium_unavailable_value%', TRUE)",
DatabricksDialect{}.BuildIsNotToastValueExpression("tbl", columns.NewColumn("bar", typing.Invalid)),
)
}
{
// Structs
assert.Equal(t,
"COALESCE(TO_VARCHAR(tbl.`foo`) NOT LIKE '%__debezium_unavailable_value%', TRUE)",
DatabricksDialect{}.BuildIsNotToastValueExpression("tbl", columns.NewColumn("foo", typing.Struct)),
)
}
{
// String
assert.Equal(t,
"COALESCE(tbl.`bar` NOT LIKE '%__debezium_unavailable_value%', TRUE)",
DatabricksDialect{}.BuildIsNotToastValueExpression("tbl", columns.NewColumn("bar", typing.String)),
)
}
}

func TestDatabricksDialect_BuildCreateTableQuery(t *testing.T) {
fakeTableID := &mocks.FakeTableIdentifier{}
fakeTableID.FullyQualifiedNameReturns("{TABLE}")
Expand Down
Loading