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>
63 lines
2.7 KiB
Python
63 lines
2.7 KiB
Python
# -*- encoding: utf-8 -*-
|
|
#
|
|
# 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 pyspark.sql.functions import sha2
|
|
from pyspark.sql.utils import AnalysisException, ParseException, IllegalArgumentException
|
|
from pyspark.testing.sqlutils import ReusedSQLTestCase
|
|
|
|
|
|
class UtilsTests(ReusedSQLTestCase):
|
|
|
|
def test_capture_analysis_exception(self):
|
|
self.assertRaises(AnalysisException, lambda: self.spark.sql("select abc"))
|
|
self.assertRaises(AnalysisException, lambda: self.df.selectExpr("a + b"))
|
|
|
|
def test_capture_user_friendly_exception(self):
|
|
try:
|
|
self.spark.sql("select `中文字段`")
|
|
except AnalysisException as e:
|
|
self.assertRegexpMatches(str(e), "cannot resolve '`中文字段`'")
|
|
|
|
def test_capture_parse_exception(self):
|
|
self.assertRaises(ParseException, lambda: self.spark.sql("abc"))
|
|
|
|
def test_capture_illegalargument_exception(self):
|
|
self.assertRaisesRegexp(IllegalArgumentException, "Setting negative mapred.reduce.tasks",
|
|
lambda: self.spark.sql("SET mapred.reduce.tasks=-1"))
|
|
df = self.spark.createDataFrame([(1, 2)], ["a", "b"])
|
|
self.assertRaisesRegexp(IllegalArgumentException, "1024 is not in the permitted values",
|
|
lambda: df.select(sha2(df.a, 1024)).collect())
|
|
try:
|
|
df.select(sha2(df.a, 1024)).collect()
|
|
except IllegalArgumentException as e:
|
|
self.assertRegexpMatches(e.desc, "1024 is not in the permitted values")
|
|
self.assertRegexpMatches(e.stackTrace,
|
|
"org.apache.spark.sql.functions")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.sql.tests.test_utils import * # noqa: F401
|
|
|
|
try:
|
|
import xmlrunner # type: ignore[import]
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|