[
https://issues.apache.org/jira/browse/SPARK-41902?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41902:
----------------------------------
Description:
{code:java}
from pyspark.sql.functions import flatten, struct, transform
df = self.spark.sql("SELECT array(1, 2, 3) as numbers, array('a', 'b', 'c') as
letters")
actual = df.select(
flatten(
transform(
"numbers",
lambda number: transform(
"letters", lambda letter: struct(number.alias("n"),
letter.alias("l"))
),
)
)
).first()[0]
expected = [
(1, "a"),
(1, "b"),
(1, "c"),
(2, "a"),
(2, "b"),
(2, "c"),
(3, "a"),
(3, "b"),
(3, "c"),
]
self.assertEquals(actual, expected){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 809, in test_nested_higher_order_function
self.assertEquals(actual, expected)
AssertionError: Lists differ: [{'n': 'a', 'l': 'a'}, {'n': 'b', 'l': 'b'[151
chars]'c'}] != [(1, 'a'), (1, 'b'), (1, 'c'), (2, 'a'), ([43 chars]'c')]
First differing element 0:
{'n': 'a', 'l': 'a'}
(1, 'a')
- [{'l': 'a', 'n': 'a'},
- {'l': 'b', 'n': 'b'},
- {'l': 'c', 'n': 'c'},
- {'l': 'a', 'n': 'a'},
- {'l': 'b', 'n': 'b'},
- {'l': 'c', 'n': 'c'},
- {'l': 'a', 'n': 'a'},
- {'l': 'b', 'n': 'b'},
- {'l': 'c', 'n': 'c'}]
+ [(1, 'a'),
+ (1, 'b'),
+ (1, 'c'),
+ (2, 'a'),
+ (2, 'b'),
+ (2, 'c'),
+ (3, 'a'),
+ (3, 'b'),
+ (3, 'c')]
{code}
was:
{code:java}
expected = {"a": 1, "b": 2}
expected2 = {"c": 3, "d": 4}
df = self.spark.createDataFrame(
[(list(expected.keys()), list(expected.values()))], ["k", "v"]
)
actual = (
df.select(
expr("map('c', 3, 'd', 4) as dict2"),
map_from_arrays(df.k, df.v).alias("dict"),
"*",
)
.select(
map_contains_key("dict", "a").alias("one"),
map_contains_key("dict", "d").alias("not_exists"),
map_keys("dict").alias("keys"),
map_values("dict").alias("values"),
map_entries("dict").alias("items"),
"*",
)
.select(
map_concat("dict", "dict2").alias("merged"),
map_from_entries(arrays_zip("keys", "values")).alias("from_items"),
"*",
)
.first()
)
self.assertEqual(expected, actual["dict"]){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 1142, in test_map_functions
self.assertEqual(expected, actual["dict"])
AssertionError: {'a': 1, 'b': 2} != [('a', 1), ('b', 2)]{code}
Summary: Parity in String representation of higher_order_function
(was: Fix String representation of maps created by `map_from_arrays`)
> Parity in String representation of higher_order_function
> --------------------------------------------------------
>
> Key: SPARK-41902
> URL: https://issues.apache.org/jira/browse/SPARK-41902
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> from pyspark.sql.functions import flatten, struct, transform
> df = self.spark.sql("SELECT array(1, 2, 3) as numbers, array('a', 'b', 'c')
> as letters")
> actual = df.select(
> flatten(
> transform(
> "numbers",
> lambda number: transform(
> "letters", lambda letter: struct(number.alias("n"),
> letter.alias("l"))
> ),
> )
> )
> ).first()[0]
> expected = [
> (1, "a"),
> (1, "b"),
> (1, "c"),
> (2, "a"),
> (2, "b"),
> (2, "c"),
> (3, "a"),
> (3, "b"),
> (3, "c"),
> ]
> self.assertEquals(actual, expected){code}
> {code:java}
> Traceback (most recent call last):
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
> line 809, in test_nested_higher_order_function
> self.assertEquals(actual, expected)
> AssertionError: Lists differ: [{'n': 'a', 'l': 'a'}, {'n': 'b', 'l': 'b'[151
> chars]'c'}] != [(1, 'a'), (1, 'b'), (1, 'c'), (2, 'a'), ([43 chars]'c')]
> First differing element 0:
> {'n': 'a', 'l': 'a'}
> (1, 'a')
> - [{'l': 'a', 'n': 'a'},
> - {'l': 'b', 'n': 'b'},
> - {'l': 'c', 'n': 'c'},
> - {'l': 'a', 'n': 'a'},
> - {'l': 'b', 'n': 'b'},
> - {'l': 'c', 'n': 'c'},
> - {'l': 'a', 'n': 'a'},
> - {'l': 'b', 'n': 'b'},
> - {'l': 'c', 'n': 'c'}]
> + [(1, 'a'),
> + (1, 'b'),
> + (1, 'c'),
> + (2, 'a'),
> + (2, 'b'),
> + (2, 'c'),
> + (3, 'a'),
> + (3, 'b'),
> + (3, 'c')]
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
