[SPARK-35019][PYTHON][SQL] Fix type hints mismatches in pyspark.sql.*

### What changes were proposed in this pull request?
Fix type hints mismatches in pyspark.sql.*

### Why are the changes needed?
There were some mismatches in pyspark.sql.*

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
dev/lint-python passed.

Closes #32122 from Yikun/SPARK-35019.

Authored-by: Yikun Jiang <yikunkero@gmail.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>

python/pyspark/sql/catalog.pyi

@@ -17,6 +17,7 @@
 # under the License.
 
 from typing import Any, Callable, List, Optional
+from pyspark.sql._typing import UserDefinedFunctionLike
 from pyspark.sql.dataframe import DataFrame
 from pyspark.sql.session import SparkSession
 from pyspark.sql.types import DataType, StructType
@@ -53,7 +54,7 @@ class Catalog:
     def dropGlobalTempView(self, viewName: str) -> None: ...
     def registerFunction(
         self, name: str, f: Callable[..., Any], returnType: DataType = ...
-    ) -> None: ...
+    ) -> UserDefinedFunctionLike: ...
     def isCached(self, tableName: str) -> bool: ...
     def cacheTable(self, tableName: str) -> None: ...
     def uncacheTable(self, tableName: str) -> None: ...

python/pyspark/sql/conf.pyi

@@ -21,7 +21,7 @@ from py4j.java_gateway import JavaObject  # type: ignore[import]
 
 class RuntimeConfig:
     def __init__(self, jconf: JavaObject) -> None: ...
-    def set(self, key: str, value: str) -> str: ...
+    def set(self, key: str, value: str) -> None: ...
     def get(self, key: str, default: Optional[str] = ...) -> str: ...
     def unset(self, key: str) -> None: ...
     def isModifiable(self, key: str) -> bool: ...

python/pyspark/sql/context.pyi

@@ -15,6 +15,7 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+from pyspark.sql._typing import UserDefinedFunctionLike
 
 from typing import overload
 from typing import Any, Callable, Iterable, List, Optional, Tuple, TypeVar, Union
@@ -63,7 +64,7 @@ class SQLContext:
     ) -> DataFrame: ...
     def registerFunction(
         self, name: str, f: Callable[..., Any], returnType: DataType = ...
-    ) -> None: ...
+    ) -> UserDefinedFunctionLike: ...
     def registerJavaFunction(
         self, name: str, javaClassName: str, returnType: Optional[DataType] = ...
     ) -> None: ...

python/pyspark/sql/dataframe.py

@@ -588,7 +588,7 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
 
         Parameters
         ----------
-        eventTime : str or :class:`Column`
+        eventTime : str
             the name of the column that contains the event time of the row.
         delayThreshold : str
             the minimum delay to wait to data to arrive late, relative to the

python/pyspark/sql/dataframe.pyi

@@ -85,7 +85,7 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
     def checkpoint(self, eager: bool = ...) -> DataFrame: ...
     def localCheckpoint(self, eager: bool = ...) -> DataFrame: ...
     def withWatermark(
-        self, eventTime: ColumnOrName, delayThreshold: str
+        self, eventTime: str, delayThreshold: str
     ) -> DataFrame: ...
     def hint(self, name: str, *parameters: Union[PrimitiveType, List[PrimitiveType]]) -> DataFrame: ...
     def count(self) -> int: ...

python/pyspark/sql/functions.pyi

@@ -57,7 +57,7 @@ def monotonically_increasing_id() -> Column: ...
 def nanvl(col1: ColumnOrName, col2: ColumnOrName) -> Column: ...
 def percentile_approx(
     col: ColumnOrName,
-    percentage: Union[Column, float, List[float]],
+    percentage: Union[Column, float, List[float], tuple[float]],
     accuracy: Union[Column, float] = ...,
 ) -> Column: ...
 def rand(seed: Optional[int] = ...) -> Column: ...