Skip to content

Fix(hive): STRUCT column names and data type should be separated by ':' #5147

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

Merged
georgesittas merged 1 commit into from
May 31, 2025
Merged

Fix(hive): STRUCT column names and data type should be separated by ':' #5147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 11 additions & 0 deletions sqlglot/dialects/hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -741,6 +741,17 @@ def struct_sql(self, expression: exp.Struct) -> str:

return self.func("STRUCT", *values)

def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
return super().columndef_sql(
expression,
sep=(
": "
if isinstance(expression.parent, exp.DataType)
and expression.parent.is_type("struct")
else sep
),
)

def alterset_sql(self, expression: exp.AlterSet) -> str:
exprs = self.expressions(expression, flat=True)
exprs = f" {exprs}" if exprs else ""
Expand Down
11 changes: 0 additions & 11 deletions sqlglot/dialects/spark2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,14 +347,3 @@ def cast_sql(self, expression: exp.Cast, safe_prefix: t.Optional[str] = None) ->
return self.func("TO_JSON", arg)

return super(Hive.Generator, self).cast_sql(expression, safe_prefix=safe_prefix)

def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
return super().columndef_sql(
expression,
sep=(
": "
if isinstance(expression.parent, exp.DataType)
and expression.parent.is_type("struct")
else sep
),
)
4 changes: 2 additions & 2 deletions tests/dialects/test_bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1234,7 +1234,7 @@ def test_bigquery(self):
"bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRING>)",
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b TEXT))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b VARCHAR))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRING>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
},
)
Expand All @@ -1244,7 +1244,7 @@ def test_bigquery(self):
"bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a BIGINT, struct_col_b STRUCT(nested_col_a TEXT, nested_col_b TEXT)))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a BIGINT, struct_col_b ROW(nested_col_a VARCHAR, nested_col_b VARCHAR)))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a BIGINT, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: BIGINT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: BIGINT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
},
)
Expand Down
22 changes: 22 additions & 0 deletions tests/dialects/test_hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,6 +184,28 @@ def test_ddl(self):
self.validate_identity(
"ALTER VIEW v1 UNSET TBLPROPERTIES ('tblp1', 'tblp2')", check_command_warning=True
)
self.validate_identity("CREATE TABLE foo (col STRUCT<struct_col_a: VARCHAR((50))>)")

self.validate_all(
"CREATE TABLE db.example_table (col_a struct<struct_col_a:int, struct_col_b:string>)",
write={
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b TEXT))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b VARCHAR))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
},
)

self.validate_all(
"CREATE TABLE db.example_table (col_a struct<struct_col_a:int, struct_col_b:struct<nested_col_a:string, nested_col_b:string>>)",
write={
"bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b STRUCT(nested_col_a TEXT, nested_col_b TEXT)))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b ROW(nested_col_a VARCHAR, nested_col_b VARCHAR)))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
},
)

def test_lateral_view(self):
self.validate_all(
Expand Down
4 changes: 2 additions & 2 deletions tests/dialects/test_presto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,7 +511,7 @@ def test_ddl(self):
write={
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b TEXT))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b VARCHAR))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRING>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
},
)
Expand All @@ -520,7 +520,7 @@ def test_ddl(self):
write={
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b STRUCT(nested_col_a TEXT, nested_col_b TEXT)))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b ROW(nested_col_a VARCHAR, nested_col_b VARCHAR)))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
},
)
Expand Down
4 changes: 2 additions & 2 deletions tests/dialects/test_spark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ def test_ddl(self):
write={
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b TEXT))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b VARCHAR))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRING>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
},
)
Expand All @@ -37,7 +37,7 @@ def test_ddl(self):
"bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b STRUCT(nested_col_a TEXT, nested_col_b TEXT)))",
"presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b ROW(nested_col_a VARCHAR, nested_col_b VARCHAR)))",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
"hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
"spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
},
)
Expand Down