This is an automated email from the ASF dual-hosted git repository. gurwls223 pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push: new d3f12df6e09e [SPARK-47437][PYTHON][CONNECT] Correct the error class for `DataFrame.sort*` d3f12df6e09e is described below commit d3f12df6e09ee47dbd7c9e08c9962430a2601941 Author: Ruifeng Zheng <ruife...@apache.org> AuthorDate: Mon Mar 18 20:24:43 2024 +0900 [SPARK-47437][PYTHON][CONNECT] Correct the error class for `DataFrame.sort*` ### What changes were proposed in this pull request? Correct the error class for `DataFrame.sort*` ### Why are the changes needed? `DataFrame.sort*` support negative indices, which means `sort by desc` ### Does this PR introduce _any_ user-facing change? yes ### How was this patch tested? ci ### Was this patch authored or co-authored using generative AI tooling? no Closes #45559 from zhengruifeng/correct_index_error. Authored-by: Ruifeng Zheng <ruife...@apache.org> Signed-off-by: Hyukjin Kwon <gurwls...@apache.org> --- python/pyspark/errors/error_classes.py | 5 +++++ python/pyspark/sql/connect/dataframe.py | 3 ++- python/pyspark/sql/dataframe.py | 4 ++-- 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/python/pyspark/errors/error_classes.py b/python/pyspark/errors/error_classes.py index 1e21ad3543e9..6b7f19b44918 100644 --- a/python/pyspark/errors/error_classes.py +++ b/python/pyspark/errors/error_classes.py @@ -1162,6 +1162,11 @@ ERROR_CLASSES_JSON = ''' "message": [ "Function `<func_name>` should take at least <num_cols> columns." ] + }, + "ZERO_INDEX": { + "message": [ + "Index must be non-zero." + ] } } ''' diff --git a/python/pyspark/sql/connect/dataframe.py b/python/pyspark/sql/connect/dataframe.py index bbb1be4c4724..f300774b6e57 100644 --- a/python/pyspark/sql/connect/dataframe.py +++ b/python/pyspark/sql/connect/dataframe.py @@ -701,7 +701,8 @@ class DataFrame: _c = self[-c - 1].desc() else: raise PySparkIndexError( - error_class="INDEX_NOT_POSITIVE", message_parameters={"index": str(c)} + error_class="ZERO_INDEX", + message_parameters={}, ) else: _c = c # type: ignore[assignment] diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 5c5c263b8156..d04c35dac5e9 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -3331,7 +3331,6 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin): jcols = [] for c in cols: if isinstance(c, int) and not isinstance(c, bool): - # TODO: should introduce dedicated error class # ordinal is 1-based if c > 0: _c = self[c - 1] @@ -3340,7 +3339,8 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin): _c = self[-c - 1].desc() else: raise PySparkIndexError( - error_class="INDEX_NOT_POSITIVE", message_parameters={"index": str(c)} + error_class="ZERO_INDEX", + message_parameters={}, ) else: _c = c # type: ignore[assignment] --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org