You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Sandeep Singh (Jira)" <ji...@apache.org> on 2023/01/03 02:46:00 UTC
[jira] [Updated] (SPARK-41849) Implement DataFrameReader.text
[ https://issues.apache.org/jira/browse/SPARK-41849?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sandeep Singh updated SPARK-41849:
----------------------------------
Description:
{code:java}
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 276, in pyspark.sql.connect.functions.input_file_name
Failed example:
df = spark.read.text(path)
Exception raised:
Traceback (most recent call last):
File "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py", line 1350, in __run
exec(compile(example.source, filename, "single",
File "<doctest pyspark.sql.connect.functions.input_file_name[2]>", line 1, in <module>
df = spark.read.text(path)
AttributeError: 'DataFrameReader' object has no attribute 'text'{code}
was:
{code:java}
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 1270, in pyspark.sql.connect.functions.explode
Failed example:
eDF.select(explode(eDF.mapfield).alias("key", "value")).show()
Exception raised:
Traceback (most recent call last):
File "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py", line 1350, in __run
exec(compile(example.source, filename, "single",
File "<doctest pyspark.sql.connect.functions.explode[3]>", line 1, in <module>
eDF.select(explode(eDF.mapfield).alias("key", "value")).show()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 534, in show
print(self._show_string(n, truncate, vertical))
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 423, in _show_string
).toPandas()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1031, in toPandas
return self._session.client.to_pandas(query)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 413, in to_pandas
return self._execute_and_fetch(req)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 573, in _execute_and_fetch
self._handle_error(rpc_error)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 619, in _handle_error
raise SparkConnectAnalysisException(
pyspark.sql.connect.client.SparkConnectAnalysisException: [INVALID_COLUMN_OR_FIELD_DATA_TYPE] Column or field `mapfield` is of type "STRUCT<a: STRING>" while it's required to be "MAP<STRING, STRING>".
Plan: {code}
{code:java}
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 1364, in pyspark.sql.connect.functions.inline
Failed example:
df.select(inline(df.structlist)).show()
Exception raised:
Traceback (most recent call last):
File "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py", line 1350, in __run
exec(compile(example.source, filename, "single",
File "<doctest pyspark.sql.connect.functions.inline[2]>", line 1, in <module>
df.select(inline(df.structlist)).show()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 534, in show
print(self._show_string(n, truncate, vertical))
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 423, in _show_string
).toPandas()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1031, in toPandas
return self._session.client.to_pandas(query)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 413, in to_pandas
return self._execute_and_fetch(req)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 573, in _execute_and_fetch
self._handle_error(rpc_error)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 619, in _handle_error
raise SparkConnectAnalysisException(
pyspark.sql.connect.client.SparkConnectAnalysisException: [INVALID_COLUMN_OR_FIELD_DATA_TYPE] Column or field `structlist`.`element` is of type "ARRAY<BIGINT>" while it's required to be "STRUCT<a: BIGINT, b: BIGINT>".
Plan: {code}
> Implement DataFrameReader.text
> ------------------------------
>
> Key: SPARK-41849
> URL: https://issues.apache.org/jira/browse/SPARK-41849
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 276, in pyspark.sql.connect.functions.input_file_name
> Failed example:
> df = spark.read.text(path)
> Exception raised:
> Traceback (most recent call last):
> File "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py", line 1350, in __run
> exec(compile(example.source, filename, "single",
> File "<doctest pyspark.sql.connect.functions.input_file_name[2]>", line 1, in <module>
> df = spark.read.text(path)
> AttributeError: 'DataFrameReader' object has no attribute 'text'{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org