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>
76 lines
2.8 KiB
Python
76 lines
2.8 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, TypeVar, Union
|
|
|
|
from py4j.java_gateway import JavaObject # type: ignore[import]
|
|
|
|
from pyspark.context import SparkContext
|
|
from pyspark.rdd import RDD
|
|
from pyspark.storagelevel import StorageLevel
|
|
from pyspark.streaming.dstream import DStream
|
|
from pyspark.streaming.listener import StreamingListener
|
|
|
|
T = TypeVar("T")
|
|
|
|
class StreamingContext:
|
|
def __init__(
|
|
self,
|
|
sparkContext: SparkContext,
|
|
batchDuration: Union[float, int] = ...,
|
|
jssc: Optional[JavaObject] = ...,
|
|
) -> None: ...
|
|
@classmethod
|
|
def getOrCreate(
|
|
cls, checkpointPath: str, setupFunc: Callable[[], StreamingContext]
|
|
) -> StreamingContext: ...
|
|
@classmethod
|
|
def getActive(cls) -> StreamingContext: ...
|
|
@classmethod
|
|
def getActiveOrCreate(
|
|
cls, checkpointPath: str, setupFunc: Callable[[], StreamingContext]
|
|
) -> StreamingContext: ...
|
|
@property
|
|
def sparkContext(self) -> SparkContext: ...
|
|
def start(self) -> None: ...
|
|
def awaitTermination(self, timeout: Optional[int] = ...) -> None: ...
|
|
def awaitTerminationOrTimeout(self, timeout: int) -> None: ...
|
|
def stop(
|
|
self, stopSparkContext: bool = ..., stopGraceFully: bool = ...
|
|
) -> None: ...
|
|
def remember(self, duration: int) -> None: ...
|
|
def checkpoint(self, directory: str) -> None: ...
|
|
def socketTextStream(
|
|
self, hostname: str, port: int, storageLevel: StorageLevel = ...
|
|
) -> DStream[str]: ...
|
|
def textFileStream(self, directory: str) -> DStream[str]: ...
|
|
def binaryRecordsStream(
|
|
self, directory: str, recordLength: int
|
|
) -> DStream[bytes]: ...
|
|
def queueStream(
|
|
self,
|
|
rdds: List[RDD[T]],
|
|
oneAtATime: bool = ...,
|
|
default: Optional[RDD[T]] = ...,
|
|
) -> DStream[T]: ...
|
|
def transform(
|
|
self, dstreams: List[DStream[Any]], transformFunc: Callable[..., RDD[T]]
|
|
) -> DStream[T]: ...
|
|
def union(self, *dstreams: DStream[T]) -> DStream[T]: ...
|
|
def addStreamingListener(self, streamingListener: StreamingListener) -> None: ...
|