31a16fbb40
### What changes were proposed in this pull request? This PR proposes migration of [`pyspark-stubs`](https://github.com/zero323/pyspark-stubs) into Spark codebase. ### Why are the changes needed? ### Does this PR introduce _any_ user-facing change? Yes. This PR adds type annotations directly to Spark source. This can impact interaction with development tools for users, which haven't used `pyspark-stubs`. ### How was this patch tested? - [x] MyPy tests of the PySpark source ``` mypy --no-incremental --config python/mypy.ini python/pyspark ``` - [x] MyPy tests of Spark examples ``` MYPYPATH=python/ mypy --no-incremental --config python/mypy.ini examples/src/main/python/ml examples/src/main/python/sql examples/src/main/python/sql/streaming ``` - [x] Existing Flake8 linter - [x] Existing unit tests Tested against: - `mypy==0.790+dev.e959952d9001e9713d329a2f9b196705b028f894` - `mypy==0.782` Closes #29591 from zero323/SPARK-32681. Authored-by: zero323 <mszymkiewicz@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
64 lines
2.6 KiB
Python
64 lines
2.6 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one
|
|
# or more contributor license agreements. See the NOTICE file
|
|
# distributed with this work for additional information
|
|
# regarding copyright ownership. The ASF licenses this file
|
|
# to you under the Apache License, Version 2.0 (the
|
|
# "License"); you may not use this file except in compliance
|
|
# with the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing,
|
|
# software distributed under the License is distributed on an
|
|
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
|
# KIND, either express or implied. See the License for the
|
|
# specific language governing permissions and limitations
|
|
# under the License.
|
|
|
|
from typing import Any, Callable, List, Optional
|
|
from pyspark.sql.dataframe import DataFrame
|
|
from pyspark.sql.session import SparkSession
|
|
from pyspark.sql.types import DataType, StructType
|
|
from collections import namedtuple
|
|
|
|
Database = namedtuple("Database", "name description locationUri")
|
|
|
|
Table = namedtuple("Table", "name database description tableType isTemporary")
|
|
|
|
Column = namedtuple("Column", "name description dataType nullable isPartition isBucket")
|
|
|
|
Function = namedtuple("Function", "name description className isTemporary")
|
|
|
|
class Catalog:
|
|
def __init__(self, sparkSession: SparkSession) -> None: ...
|
|
def currentDatabase(self) -> str: ...
|
|
def setCurrentDatabase(self, dbName: str) -> None: ...
|
|
def listDatabases(self) -> List[Database]: ...
|
|
def listTables(self, dbName: Optional[str] = ...) -> List[Table]: ...
|
|
def listFunctions(self, dbName: Optional[str] = ...) -> List[Function]: ...
|
|
def listColumns(
|
|
self, tableName: str, dbName: Optional[str] = ...
|
|
) -> List[Column]: ...
|
|
def createTable(
|
|
self,
|
|
tableName: str,
|
|
path: Optional[str] = ...,
|
|
source: Optional[str] = ...,
|
|
schema: Optional[StructType] = ...,
|
|
description: Optional[str] = ...,
|
|
**options: str
|
|
) -> DataFrame: ...
|
|
def dropTempView(self, viewName: str) -> None: ...
|
|
def dropGlobalTempView(self, viewName: str) -> None: ...
|
|
def registerFunction(
|
|
self, name: str, f: Callable[..., Any], returnType: DataType = ...
|
|
) -> None: ...
|
|
def isCached(self, tableName: str) -> bool: ...
|
|
def cacheTable(self, tableName: str) -> None: ...
|
|
def uncacheTable(self, tableName: str) -> None: ...
|
|
def clearCache(self) -> None: ...
|
|
def refreshTable(self, tableName: str) -> None: ...
|
|
def recoverPartitions(self, tableName: str) -> None: ...
|
|
def refreshByPath(self, path: str) -> None: ...
|