itholic commented on code in PR #46123:
URL: https://github.com/apache/spark/pull/46123#discussion_r1574020712
##########
python/pyspark/sql/tests/test_functions.py:
##########
@@ -1315,6 +1315,35 @@ def test_parse_json(self):
self.assertEqual("""{"a":1}""", actual["var"])
self.assertEqual("""{"b":[{"c":"str2"}]}""", actual["var_lit"])
+ def test_variant_expressions(self):
+ df = self.spark.createDataFrame([Row(json="""{ "a" : 1 }"""),
Row(json="""{ "b" : 2 }""")])
+ v = F.parse_json(df.json)
+
+ def check(resultDf, expected):
+ self.assertEqual([r[0] for r in resultDf.collect()], expected)
+
+ check(df.select(F.is_variant_null(v)), [False, False])
+ check(df.select(F.schema_of_variant(v)), ["STRUCT<a: BIGINT>",
"STRUCT<b: BIGINT>"])
+ check(df.select(F.schema_of_variant_agg(v)), ["STRUCT<a: BIGINT, b:
BIGINT>"])
+
+ check(df.select(F.variant_get(v, "$.a", "int")), [1, None])
+ check(df.select(F.variant_get(v, "$.b", "int")), [None, 2])
+ check(df.select(F.variant_get(v, "$.a", "double")), [1.0, None])
+
+ with self.assertRaises(SparkRuntimeException) as ex:
+ df.select(F.variant_get(v, "$.a", "binary")).collect()
Review Comment:
qq: So, only `variant_get` cast an exception right?
If we have other negative cases let's add more failure test, otherwise looks
good as it is.
##########
python/pyspark/sql/tests/test_functions.py:
##########
@@ -1315,6 +1315,35 @@ def test_parse_json(self):
self.assertEqual("""{"a":1}""", actual["var"])
self.assertEqual("""{"b":[{"c":"str2"}]}""", actual["var_lit"])
+ def test_variant_expressions(self):
+ df = self.spark.createDataFrame([Row(json="""{ "a" : 1 }"""),
Row(json="""{ "b" : 2 }""")])
+ v = F.parse_json(df.json)
+
+ def check(resultDf, expected):
+ self.assertEqual([r[0] for r in resultDf.collect()], expected)
+
+ check(df.select(F.is_variant_null(v)), [False, False])
+ check(df.select(F.schema_of_variant(v)), ["STRUCT<a: BIGINT>",
"STRUCT<b: BIGINT>"])
+ check(df.select(F.schema_of_variant_agg(v)), ["STRUCT<a: BIGINT, b:
BIGINT>"])
+
+ check(df.select(F.variant_get(v, "$.a", "int")), [1, None])
+ check(df.select(F.variant_get(v, "$.b", "int")), [None, 2])
+ check(df.select(F.variant_get(v, "$.a", "double")), [1.0, None])
+
+ with self.assertRaises(SparkRuntimeException) as ex:
+ df.select(F.variant_get(v, "$.a", "binary")).collect()
Review Comment:
qq: So, only `variant_get` cast an exception, right?
If we have other negative cases let's add more failure test, otherwise looks
good as it is.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
