Skip to content

[SPARK-48555][PYTHON][FOLLOW-UP] Simplify the support of Any parameters #47110

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhengruifeng wants to merge 3 commits into from
Closed

[SPARK-48555][PYTHON][FOLLOW-UP] Simplify the support of Any parameters #47110

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8403595
init
zhengruifeng Jun 26, 2024
14f1e0b
init
zhengruifeng Jun 26, 2024
ed58bc5
init
zhengruifeng Jun 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 12 additions & 22 deletions python/pyspark/sql/functions/builtin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10938,11 +10938,15 @@ def substring(
target column to work on.
pos : :class:`~pyspark.sql.Column` or str or int
starting position in str.

.. versionchanged:: 4.0.0
`pos` now accepts column and column name.

len : :class:`~pyspark.sql.Column` or str or int
length of chars.

.. versionchanged:: 4.0.0
`pos` and `len` now also accept Columns or names of Columns.
`len` now accepts column and column name.

Returns
-------
Expand All @@ -10962,11 +10966,9 @@ def substring(
>>> df.select(substring(df.s, df.p, df.l).alias('s')).collect()
[Row(s='par')]
"""
from pyspark.sql.classic.column import _to_java_column

pos = _to_java_column(lit(pos) if isinstance(pos, int) else pos)
len = _to_java_column(lit(len) if isinstance(len, int) else len)
return _invoke_function("substring", _to_java_column(str), pos, len)
pos = lit(pos) if isinstance(pos, int) else pos
len = lit(len) if isinstance(len, int) else len
return _invoke_function_over_columns("substring", str, pos, len)


@_try_remote_functions
Expand Down Expand Up @@ -13618,10 +13620,7 @@ def array_contains(col: "ColumnOrName", value: Any) -> Column:
| true|
+----------+
"""
from pyspark.sql.classic.column import _to_java_column

value = value._jc if isinstance(value, Column) else value
return _invoke_function("array_contains", _to_java_column(col), value)
return _invoke_function_over_columns("array_contains", col, lit(value))


@_try_remote_functions
Expand Down Expand Up @@ -14064,10 +14063,7 @@ def array_position(col: "ColumnOrName", value: Any) -> Column:
+-------------------------+

"""
from pyspark.sql.classic.column import _to_java_column

value = _to_java_column(value) if isinstance(value, Column) else value
return _invoke_function("array_position", _to_java_column(col), value)
return _invoke_function_over_columns("array_position", col, lit(value))


@_try_remote_functions
Expand Down Expand Up @@ -14515,10 +14511,7 @@ def array_remove(col: "ColumnOrName", element: Any) -> Column:
| [2, 3]|
+-----------------------+
"""
from pyspark.sql.classic.column import _to_java_column

element = _to_java_column(element) if isinstance(element, Column) else element
return _invoke_function("array_remove", _to_java_column(col), element)
return _invoke_function_over_columns("array_remove", col, lit(element))


@_try_remote_functions
Expand Down Expand Up @@ -17327,10 +17320,7 @@ def map_contains_key(col: "ColumnOrName", value: Any) -> Column:
| true|
+---------------------------+
"""
from pyspark.sql.classic.column import _to_java_column

value = _to_java_column(value) if isinstance(value, Column) else value
return _invoke_function("map_contains_key", _to_java_column(col), value)
return _invoke_function_over_columns("map_contains_key", col, lit(value))


@_try_remote_functions
Expand Down