Skip to content

Commit 1db145c

Browse files
Dharin-shahevertlammerts
Dharin-shah
authored and
evertlammerts
committed
fix formatting
1 parent 84b3708 commit 1db145c

File tree

2 files changed

+65
-44
lines changed

2 files changed

+65
-44
lines changed

‎duckdb/experimental/spark/sql/types.py‎

Lines changed: 7 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -914,6 +914,7 @@ def treeString(self, level: Optional[int] = None) -> str:
914914
root
915915
|-- age: integer (nullable = true)
916916
"""
917+
917918
def _tree_string(schema: "StructType", depth: int = 0, max_depth: Optional[int] = None) -> list[str]:
918919
"""Recursively build tree string lines."""
919920
lines = []
@@ -939,7 +940,9 @@ def _tree_string(schema: "StructType", depth: int = 0, max_depth: Optional[int]
939940
element_type = field.dataType.elementType
940941
if isinstance(element_type, StructType):
941942
lines.append(f"{indent}{prefix}{field.name}: array (nullable = {nullable_str})")
942-
lines.append(f"{indent} | |-- element: struct (containsNull = {field.dataType.containsNull})")
943+
lines.append(
944+
f"{indent} | |-- element: struct (containsNull = {field.dataType.containsNull})"
945+
)
943946
nested_lines = _tree_string(element_type, depth + 2, max_depth)
944947
lines.extend(nested_lines)
945948
else:
@@ -949,7 +952,9 @@ def _tree_string(schema: "StructType", depth: int = 0, max_depth: Optional[int]
949952
elif isinstance(field.dataType, MapType):
950953
key_type = field.dataType.keyType.simpleString()
951954
value_type = field.dataType.valueType.simpleString()
952-
lines.append(f"{indent}{prefix}{field.name}: map<{key_type},{value_type}> (nullable = {nullable_str})")
955+
lines.append(
956+
f"{indent}{prefix}{field.name}: map<{key_type},{value_type}> (nullable = {nullable_str})"
957+
)
953958
# Handle simple types
954959
else:
955960
type_str = field.dataType.simpleString()

‎tests/fast/spark/test_spark_dataframe.py‎

Lines changed: 58 additions & 42 deletions
Original file line numberDiff line numberDiff line change
@@ -438,25 +438,29 @@ def test_dtypes(self, spark):
438438
for col_name, col_type in dtypes:
439439
assert isinstance(col_name, str)
440440
assert isinstance(col_type, str)
441-
441+
442442
col_names = [name for name, _ in dtypes]
443443
assert col_names == ["name", "age", "salary"]
444444
for _, col_type in dtypes:
445-
assert len(col_type) > 0
445+
assert len(col_type) > 0
446446

447447
def test_dtypes_complex_types(self, spark):
448448
from spark_namespace.sql.types import ArrayType, IntegerType, StringType, StructField, StructType
449-
schema = StructType([
450-
StructField("name", StringType(), True),
451-
StructField("scores", ArrayType(IntegerType()), True),
452-
StructField("address", StructType([
453-
StructField("city", StringType(), True),
454-
StructField("zip", StringType(), True)
455-
]), True)
456-
])
449+
450+
schema = StructType(
451+
[
452+
StructField("name", StringType(), True),
453+
StructField("scores", ArrayType(IntegerType()), True),
454+
StructField(
455+
"address",
456+
StructType([StructField("city", StringType(), True), StructField("zip", StringType(), True)]),
457+
True,
458+
),
459+
]
460+
)
457461
data = [
458462
("Alice", [90, 85, 88], {"city": "NYC", "zip": "10001"}),
459-
("Bob", [75, 80, 82], {"city": "LA", "zip": "90001"})
463+
("Bob", [75, 80, 82], {"city": "LA", "zip": "90001"}),
460464
]
461465
df = spark.createDataFrame(data, schema)
462466
dtypes = df.dtypes
@@ -481,17 +485,21 @@ def test_printSchema(self, spark, capsys):
481485

482486
def test_printSchema_nested(self, spark, capsys):
483487
from spark_namespace.sql.types import ArrayType, IntegerType, StringType, StructField, StructType
484-
schema = StructType([
485-
StructField("id", IntegerType(), True),
486-
StructField("person", StructType([
487-
StructField("name", StringType(), True),
488-
StructField("age", IntegerType(), True)
489-
]), True),
490-
StructField("hobbies", ArrayType(StringType()), True)
491-
])
488+
489+
schema = StructType(
490+
[
491+
StructField("id", IntegerType(), True),
492+
StructField(
493+
"person",
494+
StructType([StructField("name", StringType(), True), StructField("age", IntegerType(), True)]),
495+
True,
496+
),
497+
StructField("hobbies", ArrayType(StringType()), True),
498+
]
499+
)
492500
data = [
493501
(1, {"name": "Alice", "age": 25}, ["reading", "coding"]),
494-
(2, {"name": "Bob", "age": 30}, ["gaming", "music"])
502+
(2, {"name": "Bob", "age": 30}, ["gaming", "music"]),
495503
]
496504
df = spark.createDataFrame(data, schema)
497505
df.printSchema()
@@ -524,13 +532,16 @@ def test_treeString_basic(self, spark):
524532
def test_treeString_nested_struct(self, spark):
525533
from spark_namespace.sql.types import IntegerType, StringType, StructField, StructType
526534

527-
schema = StructType([
528-
StructField("id", IntegerType(), True),
529-
StructField("person", StructType([
530-
StructField("name", StringType(), True),
531-
StructField("age", IntegerType(), True)
532-
]), True)
533-
])
535+
schema = StructType(
536+
[
537+
StructField("id", IntegerType(), True),
538+
StructField(
539+
"person",
540+
StructType([StructField("name", StringType(), True), StructField("age", IntegerType(), True)]),
541+
True,
542+
),
543+
]
544+
)
534545
data = [(1, {"name": "Alice", "age": 25})]
535546
df = spark.createDataFrame(data, schema)
536547
tree = df.schema.treeString()
@@ -544,15 +555,21 @@ def test_treeString_nested_struct(self, spark):
544555
def test_treeString_with_level(self, spark):
545556
from spark_namespace.sql.types import IntegerType, StringType, StructField, StructType
546557

547-
schema = StructType([
548-
StructField("id", IntegerType(), True),
549-
StructField("person", StructType([
550-
StructField("name", StringType(), True),
551-
StructField("details", StructType([
552-
StructField("address", StringType(), True)
553-
]), True)
554-
]), True)
555-
])
558+
schema = StructType(
559+
[
560+
StructField("id", IntegerType(), True),
561+
StructField(
562+
"person",
563+
StructType(
564+
[
565+
StructField("name", StringType(), True),
566+
StructField("details", StructType([StructField("address", StringType(), True)]), True),
567+
]
568+
),
569+
True,
570+
),
571+
]
572+
)
556573

557574
data = [(1, {"name": "Alice", "details": {"address": "123 Main St"}})]
558575
df = spark.createDataFrame(data, schema)
@@ -562,16 +579,15 @@ def test_treeString_with_level(self, spark):
562579
assert " |-- id:" in tree_level_1
563580
assert " |-- person: struct" in tree_level_1
564581
# Should not show nested field names at level 1
565-
lines = tree_level_1.split('\n')
566-
assert len([l for l in lines if l.strip()]) <= 3
582+
lines = tree_level_1.split("\n")
583+
assert len([line for line in lines if line.strip()]) <= 3
567584

568585
def test_treeString_array_type(self, spark):
569586
from spark_namespace.sql.types import ArrayType, StringType, StructField, StructType
570587

571-
schema = StructType([
572-
StructField("name", StringType(), True),
573-
StructField("hobbies", ArrayType(StringType()), True)
574-
])
588+
schema = StructType(
589+
[StructField("name", StringType(), True), StructField("hobbies", ArrayType(StringType()), True)]
590+
)
575591

576592
data = [("Alice", ["reading", "coding"])]
577593
df = spark.createDataFrame(data, schema)

0 commit comments

Comments
 (0)