diff options
Diffstat (limited to 'python/pyspark/sql/tests.py')
-rw-r--r-- | python/pyspark/sql/tests.py | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index b3a6a2c6a9..7c09a0cfe3 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -157,13 +157,13 @@ class SQLTests(ReusedPySparkTestCase): self.assertEqual(4, res[0]) def test_udf_with_array_type(self): - d = [Row(l=range(3), d={"key": range(5)})] + d = [Row(l=list(range(3)), d={"key": list(range(5))})] rdd = self.sc.parallelize(d) self.sqlCtx.createDataFrame(rdd).registerTempTable("test") self.sqlCtx.registerFunction("copylist", lambda l: list(l), ArrayType(IntegerType())) self.sqlCtx.registerFunction("maplen", lambda d: len(d), IntegerType()) [(l1, l2)] = self.sqlCtx.sql("select copylist(l), maplen(d) from test").collect() - self.assertEqual(range(3), l1) + self.assertEqual(list(range(3)), l1) self.assertEqual(1, l2) def test_broadcast_in_udf(self): @@ -266,7 +266,7 @@ class SQLTests(ReusedPySparkTestCase): def test_apply_schema(self): from datetime import date, datetime - rdd = self.sc.parallelize([(127, -128L, -32768, 32767, 2147483647L, 1.0, + rdd = self.sc.parallelize([(127, -128, -32768, 32767, 2147483647, 1.0, date(2010, 1, 1), datetime(2010, 1, 1, 1, 1, 1), {"a": 1}, (2,), [1, 2, 3], None)]) schema = StructType([ @@ -309,7 +309,7 @@ class SQLTests(ReusedPySparkTestCase): def test_struct_in_map(self): d = [Row(m={Row(i=1): Row(s="")})] df = self.sc.parallelize(d).toDF() - k, v = df.head().m.items()[0] + k, v = list(df.head().m.items())[0] self.assertEqual(1, k.i) self.assertEqual("", v.s) @@ -554,6 +554,9 @@ class HiveContextSQLTests(ReusedPySparkTestCase): except py4j.protocol.Py4JError: cls.sqlCtx = None return + except TypeError: + cls.sqlCtx = None + return os.unlink(cls.tempdir.name) _scala_HiveContext =\ cls.sc._jvm.org.apache.spark.sql.hive.test.TestHiveContext(cls.sc._jsc.sc()) |