@@ -432,19 +432,20 @@ def test_dtypes(self, spark):
432432 data = [("Alice" , 25 , 5000.0 ), ("Bob" , 30 , 6000.0 )]
433433 df = spark .createDataFrame (data , ["name" , "age" , "salary" ])
434434 dtypes = df .dtypes
435+
435436 assert isinstance (dtypes , list )
436437 assert len (dtypes ) == 3
437438 for col_name , col_type in dtypes :
438439 assert isinstance (col_name , str )
439440 assert isinstance (col_type , str )
441+
440442 col_names = [name for name , _ in dtypes ]
441443 assert col_names == ["name" , "age" , "salary" ]
442444 for _ , col_type in dtypes :
443- assert len (col_type ) > 0 # Should have some type string
445+ assert len (col_type ) > 0
444446
445447 def test_dtypes_complex_types (self , spark ):
446448 from spark_namespace .sql .types import ArrayType , IntegerType , StringType , StructField , StructType
447-
448449 schema = StructType ([
449450 StructField ("name" , StringType (), True ),
450451 StructField ("scores" , ArrayType (IntegerType ()), True ),
@@ -453,12 +454,10 @@ def test_dtypes_complex_types(self, spark):
453454 StructField ("zip" , StringType (), True )
454455 ]), True )
455456 ])
456-
457457 data = [
458458 ("Alice" , [90 , 85 , 88 ], {"city" : "NYC" , "zip" : "10001" }),
459459 ("Bob" , [75 , 80 , 82 ], {"city" : "LA" , "zip" : "90001" })
460460 ]
461-
462461 df = spark .createDataFrame (data , schema )
463462 dtypes = df .dtypes
464463
@@ -472,6 +471,7 @@ def test_printSchema(self, spark, capsys):
472471 df .printSchema ()
473472 captured = capsys .readouterr ()
474473 output = captured .out
474+
475475 assert "root" in output
476476 assert "name" in output
477477 assert "age" in output
@@ -480,9 +480,7 @@ def test_printSchema(self, spark, capsys):
480480 assert "int" in output .lower () or "bigint" in output .lower ()
481481
482482 def test_printSchema_nested (self , spark , capsys ):
483- # Test printSchema with nested schema
484483 from spark_namespace .sql .types import ArrayType , IntegerType , StringType , StructField , StructType
485-
486484 schema = StructType ([
487485 StructField ("id" , IntegerType (), True ),
488486 StructField ("person" , StructType ([
@@ -491,30 +489,22 @@ def test_printSchema_nested(self, spark, capsys):
491489 ]), True ),
492490 StructField ("hobbies" , ArrayType (StringType ()), True )
493491 ])
494-
495492 data = [
496493 (1 , {"name" : "Alice" , "age" : 25 }, ["reading" , "coding" ]),
497494 (2 , {"name" : "Bob" , "age" : 30 }, ["gaming" , "music" ])
498495 ]
499-
500496 df = spark .createDataFrame (data , schema )
501-
502- # Should not raise an error
503497 df .printSchema ()
504-
505498 captured = capsys .readouterr ()
506499 output = captured .out
507500
508- # Verify nested structure is shown
509501 assert "root" in output
510502 assert "person" in output
511503 assert "hobbies" in output
512504
513505 def test_printSchema_negative_level (self , spark ):
514- # Test printSchema with invalid level parameter
515506 data = [("Alice" , 25 )]
516507 df = spark .createDataFrame (data , ["name" , "age" ])
517508
518- # Should raise PySparkValueError for negative level
519509 with pytest .raises (PySparkValueError ):
520510 df .printSchema (level = - 1 )
0 commit comments