[
https://issues.apache.org/jira/browse/SPARK-41905?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41905:
----------------------------------
Description:
{code:java}
df = self.spark.createDataFrame(
[
(
[1, 2, 3],
2,
2,
),
(
[4, 5],
2,
2,
),
],
["x", "index", "len"],
)
expected = [Row(sliced=[2, 3]), Row(sliced=[5])]
self.assertTrue(
all(
[
df.select(slice(df.x, 2, 2).alias("sliced")).collect() == expected,
df.select(slice(df.x, lit(2), lit(2)).alias("sliced")).collect() ==
expected,
df.select(slice("x", "index", "len").alias("sliced")).collect() ==
expected,
]
)
)
self.assertEqual(
df.select(slice(df.x, size(df.x) - 1, lit(1)).alias("sliced")).collect(),
[Row(sliced=[2]), Row(sliced=[4])],
)
self.assertEqual(
df.select(slice(df.x, lit(1), size(df.x) - 1).alias("sliced")).collect(),
[Row(sliced=[1, 2]), Row(sliced=[4])],
){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 596, in test_slice
df.select(slice("x", "index", "len").alias("sliced")).collect() == expected,
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/utils.py", line
332, in wrapped
return getattr(functions, f.__name__)(*args, **kwargs)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1525, in slice
raise TypeError(f"start should be a Column or int, but got
{type(start).__name__}")
TypeError: start should be a Column or int, but got str{code}
was:
{code:java}
from pyspark.sql import Window
from pyspark.sql.functions import nth_value
df = self.spark.createDataFrame(
[
("a", 0, None),
("a", 1, "x"),
("a", 2, "y"),
("a", 3, "z"),
("a", 4, None),
("b", 1, None),
("b", 2, None),
],
schema=("key", "order", "value"),
)
w = Window.partitionBy("key").orderBy("order")
rs = df.select(
df.key,
df.order,
nth_value("value", 2).over(w),
nth_value("value", 2, False).over(w),
nth_value("value", 2, True).over(w),
).collect()
expected = [
("a", 0, None, None, None),
("a", 1, "x", "x", None),
("a", 2, "x", "x", "y"),
("a", 3, "x", "x", "y"),
("a", 4, "x", "x", "y"),
("b", 1, None, None, None),
("b", 2, None, None, None),
]
for r, ex in zip(sorted(rs), sorted(expected)):
self.assertEqual(tuple(r), ex[: len(r)]){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 755, in test_nth_value
self.assertEqual(tuple(r), ex[: len(r)])
AssertionError: Tuples differ: ('a', 1, 'x', None) != ('a', 1, 'x', 'x')
First differing element 3:
None
'x'
- ('a', 1, 'x', None)
? ^^^^
+ ('a', 1, 'x', 'x')
? ^^^
{code}
> Function `slice` should handle string in params
> -----------------------------------------------
>
> Key: SPARK-41905
> URL: https://issues.apache.org/jira/browse/SPARK-41905
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> df = self.spark.createDataFrame(
> [
> (
> [1, 2, 3],
> 2,
> 2,
> ),
> (
> [4, 5],
> 2,
> 2,
> ),
> ],
> ["x", "index", "len"],
> )
> expected = [Row(sliced=[2, 3]), Row(sliced=[5])]
> self.assertTrue(
> all(
> [
> df.select(slice(df.x, 2, 2).alias("sliced")).collect() ==
> expected,
> df.select(slice(df.x, lit(2), lit(2)).alias("sliced")).collect()
> == expected,
> df.select(slice("x", "index", "len").alias("sliced")).collect()
> == expected,
> ]
> )
> )
> self.assertEqual(
> df.select(slice(df.x, size(df.x) - 1, lit(1)).alias("sliced")).collect(),
> [Row(sliced=[2]), Row(sliced=[4])],
> )
> self.assertEqual(
> df.select(slice(df.x, lit(1), size(df.x) - 1).alias("sliced")).collect(),
> [Row(sliced=[1, 2]), Row(sliced=[4])],
> ){code}
> {code:java}
> Traceback (most recent call last):
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
> line 596, in test_slice
> df.select(slice("x", "index", "len").alias("sliced")).collect() ==
> expected,
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/utils.py", line
> 332, in wrapped
> return getattr(functions, f.__name__)(*args, **kwargs)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
> line 1525, in slice
> raise TypeError(f"start should be a Column or int, but got
> {type(start).__name__}")
> TypeError: start should be a Column or int, but got str{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
