[ https://issues.apache.org/jira/browse/SPARK-41847?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sandeep Singh updated SPARK-41847: ---------------------------------- Description: {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} was: {code:java} File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 1098, in pyspark.sql.connect.functions.rank Failed example: df.withColumn("drank", rank().over(w)).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.rank[3]>", line 1, in <module> df.withColumn("drank", rank().over(w)).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: [UNRESOLVED_COLUMN.WITH_SUGGESTION] A column or function parameter with name `value` cannot be resolved. Did you mean one of the following? [`_1`] Plan: 'Project [_1#4000L, rank() windowspecdefinition('value ASC NULLS FIRST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS drank#4003] +- Project [0#3998L AS _1#4000L] +- LocalRelation [0#3998L] {code} {code:java} File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 1032, in pyspark.sql.connect.functions.cume_dist Failed example: df.withColumn("cd", cume_dist().over(w)).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.cume_dist[3]>", line 1, in <module> df.withColumn("cd", cume_dist().over(w)).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: [UNRESOLVED_COLUMN.WITH_SUGGESTION] A column or function parameter with name `value` cannot be resolved. Did you mean one of the following? [`_1`] Plan: 'Project [_1#2202L, cume_dist() windowspecdefinition('value ASC NULLS FIRST, specifiedwindowframe(RangeFrame, unboundedpreceding$(), currentrow$())) AS cd#2205] +- Project [0#2200L AS _1#2202L] +- LocalRelation [0#2200L] {code} > DataFrame mapfield invalid type > ------------------------------- > > Key: SPARK-41847 > URL: https://issues.apache.org/jira/browse/SPARK-41847 > 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 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} -- 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