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 a6db459328d [MINOR] Removing redundant parentheses from SQL function docs a6db459328d is described below commit a6db459328d7aa75e43097ddf2286c146646810a Author: panbingkun <pbk1...@gmail.com> AuthorDate: Fri Jul 14 08:40:21 2023 +0900 [MINOR] Removing redundant parentheses from SQL function docs ### What changes were proposed in this pull request? The pr aims to removing redundant parentheses from SQL function docs. ### Why are the changes needed? Make the document clearer, reduce misunderstandings. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? - Manually test. Closes #41984 from panbingkun/minor_function_docs. Authored-by: panbingkun <pbk1...@gmail.com> Signed-off-by: Hyukjin Kwon <gurwls...@apache.org> --- python/pyspark/sql/connect/functions.py | 2 +- python/pyspark/sql/functions.py | 4 ++-- .../spark/sql/catalyst/expressions/aggregate/MaxByAndMinBy.scala | 4 ++-- .../org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala | 2 +- sql/core/src/test/resources/sql-functions/sql-expression-schema.md | 4 ++-- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/python/pyspark/sql/connect/functions.py b/python/pyspark/sql/connect/functions.py index c6445f110c0..1be759d9b6e 100644 --- a/python/pyspark/sql/connect/functions.py +++ b/python/pyspark/sql/connect/functions.py @@ -195,7 +195,7 @@ def _invoke_higher_order_function( :param name: Name of the expression :param cols: a list of columns - :param funs: a list of((*Column) -> Column functions. + :param funs: a list of (*Column) -> Column functions. :return: a Column """ diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index d7a2f529fa6..b2017627598 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -12770,7 +12770,7 @@ def arrays_zip(*cols: "ColumnOrName") -> Column: Examples -------- >>> from pyspark.sql.functions import arrays_zip - >>> df = spark.createDataFrame([(([1, 2, 3], [2, 4, 6], [3, 6]))], ['vals1', 'vals2', 'vals3']) + >>> df = spark.createDataFrame([([1, 2, 3], [2, 4, 6], [3, 6])], ['vals1', 'vals2', 'vals3']) >>> df = df.select(arrays_zip(df.vals1, df.vals2, df.vals3).alias('zipped')) >>> df.show(truncate=False) +------------------------------------+ @@ -13041,7 +13041,7 @@ def _invoke_higher_order_function( :param name: Name of the expression :param cols: a list of columns - :param funs: a list of((*Column) -> Column functions. + :param funs: a list of (*Column) -> Column functions. :return: a Column """ diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxByAndMinBy.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxByAndMinBy.scala index 096a42686a3..56941c9de45 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxByAndMinBy.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MaxByAndMinBy.scala @@ -96,7 +96,7 @@ abstract class MaxMinBy extends DeclarativeAggregate with BinaryLike[Expression] usage = "_FUNC_(x, y) - Returns the value of `x` associated with the maximum value of `y`.", examples = """ Examples: - > SELECT _FUNC_(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y); + > SELECT _FUNC_(x, y) FROM VALUES ('a', 10), ('b', 50), ('c', 20) AS tab(x, y); b """, group = "agg_funcs", @@ -119,7 +119,7 @@ case class MaxBy(valueExpr: Expression, orderingExpr: Expression) extends MaxMin usage = "_FUNC_(x, y) - Returns the value of `x` associated with the minimum value of `y`.", examples = """ Examples: - > SELECT _FUNC_(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y); + > SELECT _FUNC_(x, y) FROM VALUES ('a', 10), ('b', 50), ('c', 20) AS tab(x, y); a """, group = "agg_funcs", diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala index 32c41cba4e1..0bbae04fb89 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala @@ -663,7 +663,7 @@ case class JsonToStructs( {"[1]":{"b":2}} > SELECT _FUNC_(map('a', 1)); {"a":1} - > SELECT _FUNC_(array((map('a', 1)))); + > SELECT _FUNC_(array(map('a', 1))); [{"a":1}] """, group = "json_funcs", diff --git a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md index 11dca77fada..71fde8c7268 100644 --- a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md +++ b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md @@ -398,10 +398,10 @@ | org.apache.spark.sql.catalyst.expressions.aggregate.Last | last | SELECT last(col) FROM VALUES (10), (5), (20) AS tab(col) | struct<last(col):int> | | org.apache.spark.sql.catalyst.expressions.aggregate.Last | last_value | SELECT last_value(col) FROM VALUES (10), (5), (20) AS tab(col) | struct<last_value(col):int> | | org.apache.spark.sql.catalyst.expressions.aggregate.Max | max | SELECT max(col) FROM VALUES (10), (50), (20) AS tab(col) | struct<max(col):int> | -| org.apache.spark.sql.catalyst.expressions.aggregate.MaxBy | max_by | SELECT max_by(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y) | struct<max_by(x, y):string> | +| org.apache.spark.sql.catalyst.expressions.aggregate.MaxBy | max_by | SELECT max_by(x, y) FROM VALUES ('a', 10), ('b', 50), ('c', 20) AS tab(x, y) | struct<max_by(x, y):string> | | org.apache.spark.sql.catalyst.expressions.aggregate.Median | median | SELECT median(col) FROM VALUES (0), (10) AS tab(col) | struct<median(col):double> | | org.apache.spark.sql.catalyst.expressions.aggregate.Min | min | SELECT min(col) FROM VALUES (10), (-1), (20) AS tab(col) | struct<min(col):int> | -| org.apache.spark.sql.catalyst.expressions.aggregate.MinBy | min_by | SELECT min_by(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y) | struct<min_by(x, y):string> | +| org.apache.spark.sql.catalyst.expressions.aggregate.MinBy | min_by | SELECT min_by(x, y) FROM VALUES ('a', 10), ('b', 50), ('c', 20) AS tab(x, y) | struct<min_by(x, y):string> | | org.apache.spark.sql.catalyst.expressions.aggregate.Mode | mode | SELECT mode(col) FROM VALUES (0), (10), (10) AS tab(col) | struct<mode(col):int> | | org.apache.spark.sql.catalyst.expressions.aggregate.Percentile | percentile | SELECT percentile(col, 0.3) FROM VALUES (0), (10) AS tab(col) | struct<percentile(col, 0.3, 1):double> | | org.apache.spark.sql.catalyst.expressions.aggregate.RegrAvgX | regr_avgx | SELECT regr_avgx(y, x) FROM VALUES (1, 2), (2, 2), (2, 3), (2, 4) AS tab(y, x) | struct<regr_avgx(y, x):double> | --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org