03dd33cc98
### What changes were proposed in this pull request?
This PR fixes an issue that `sql` method in the following classes which take qualified names don't quote the qualified names properly.
* UnresolvedAttribute
* AttributeReference
* Alias
One instance caused by this issue is reported in SPARK-34626.
```
UnresolvedAttribute("a" :: "b" :: Nil).sql
`a.b` // expected: `a`.`b`
```
And other instances are like as follows.
```
UnresolvedAttribute("a`b"::"c.d"::Nil).sql
a`b.`c.d` // expected: `a``b`.`c.d`
AttributeReference("a.b", IntegerType)(qualifier = "c.d"::Nil).sql
c.d.`a.b` // expected: `c.d`.`a.b`
Alias(AttributeReference("a", IntegerType)(), "b.c")(qualifier = "d.e"::Nil).sql
`a` AS d.e.`b.c` // expected: `a` AS `d.e`.`b.c`
```
### Why are the changes needed?
This is a bug.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
New test.
Closes #31754 from sarutak/fix-qualified-names.
Authored-by: Kousuke Saruta <sarutak@oss.nttdata.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
62 lines
2.6 KiB
Python
62 lines
2.6 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.assertRegex(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.assertRaisesRegex(IllegalArgumentException, "Setting negative mapred.reduce.tasks",
|
|
lambda: self.spark.sql("SET mapred.reduce.tasks=-1"))
|
|
df = self.spark.createDataFrame([(1, 2)], ["a", "b"])
|
|
self.assertRaisesRegex(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.assertRegex(e.desc, "1024 is not in the permitted values")
|
|
self.assertRegex(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)
|