Sandeep Singh created SPARK-41901:
-------------------------------------
Summary: Parity in String representation of Column
Key: SPARK-41901
URL: https://issues.apache.org/jira/browse/SPARK-41901
Project: Spark
Issue Type: Sub-task
Components: Connect
Affects Versions: 3.4.0
Reporter: Sandeep Singh
{code:java}
dt = datetime.date(2021, 12, 27)
# Note; number var in Python gets converted to LongType column;
# this is not supported by the function, so cast to Integer explicitly
df = self.spark.createDataFrame([Row(date=dt, add=2)], "date date, add integer")
self.assertTrue(
all(
df.select(
date_add(df.date, df.add) == datetime.date(2021, 12, 29),
date_add(df.date, "add") == datetime.date(2021, 12, 29),
date_add(df.date, 3) == datetime.date(2021, 12, 30),
).first()
)
){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 391, in test_date_add_function
).first()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 246, in first
return self.head()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 310, in head
rs = self.head(1)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 312, in head
return self.take(n)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 317, in take
return self.limit(num).collect()
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py",
line 1076, in collect
table = self._session.client.to_table(query)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
414, in to_table
table, _ = self._execute_and_fetch(req)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
586, in _execute_and_fetch
self._handle_error(rpc_error)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line
625, in _handle_error
raise SparkConnectAnalysisException(
pyspark.sql.connect.client.SparkConnectAnalysisException:
[DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE] Cannot resolve "date_add(date, add)"
due to data type mismatch: Parameter 2 requires the ("INT" or "SMALLINT" or
"TINYINT") type, however "add" has the type "BIGINT".
Plan: 'GlobalLimit 1
+- 'LocalLimit 1
+- 'Project [unresolvedalias('`==`(date_add(date#753, add#754L),
2021-12-29), None), unresolvedalias('`==`(date_add(date#753, add#754L),
2021-12-29), None), (date_add(date#753, 3) = 2021-12-30) AS (date_add(date, 3)
= DATE '2021-12-30')#759]
+- Project [date#753, add#754L]
+- Project [date#749 AS date#753, add#750L AS add#754L]
+- LocalRelation [date#749, add#750L]{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
