203bf9e569
### What changes were proposed in this pull request?
The str of `CapaturedException` is now returned by str(self.desc) rather than repr(self.desc), which is more user-friendly. It also handles unicode under python2 specially.
### Why are the changes needed?
This is an improvement, and makes exception more human readable in python side.
### Does this PR introduce any user-facing change?
Before this pr, select `中文字段` throws exception something likes below:
```
Traceback (most recent call last):
File "/Users/advancedxy/code_workspace/github/spark/python/pyspark/sql/tests/test_utils.py", line 34, in test_capture_user_friendly_exception
raise e
AnalysisException: u"cannot resolve '`\u4e2d\u6587\u5b57\u6bb5`' given input columns: []; line 1 pos 7;\n'Project ['\u4e2d\u6587\u5b57\u6bb5]\n+- OneRowRelation\n"
```
after this pr:
```
Traceback (most recent call last):
File "/Users/advancedxy/code_workspace/github/spark/python/pyspark/sql/tests/test_utils.py", line 34, in test_capture_user_friendly_exception
raise e
AnalysisException: cannot resolve '`中文字段`' given input columns: []; line 1 pos 7;
'Project ['中文字段]
+- OneRowRelation
```
### How was this patch
Add a new test to verify unicode are correctly converted and manual checks for thrown exceptions.
This pr's credits should go to uncleGen and is based on https://github.com/apache/spark/pull/17267
Closes #25814 from advancedxy/python_exception_19926_and_21045.
Authored-by: Xianjin YE <advancedxy@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 *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|