mirror of
https://github.com/apache/impala.git
synced 2025-12-30 12:02:10 -05:00
ffa7829b70
For files that have a Cloudera copyright (and no other copyright notice), make changes to follow the ASF source file header policy here: http://www.apache.org/legal/src-headers.html#headers Specifically: 1) Remove the Cloudera copyright. 2) Modify NOTICE.txt according to http://www.apache.org/legal/src-headers.html#notice to follow that format and add a line for Cloudera. 3) Replace or add the existing ASF license text with the one given on the website. Much of this change was automatically generated via: git grep -li 'Copyright.*Cloudera' > modified_files.txt cat modified_files.txt | xargs perl -n -i -e 'print unless m#Copyright.*Cloudera#i;' cat modified_files_txt | xargs fix_apache_license.py [1] Some manual fixups were performed following those steps, especially when license text was completely missing from the file. [1] https://gist.github.com/anonymous/ff71292094362fc5c594 with minor modification to ORIG_LICENSE to match Impala's license text. Change-Id: I2e0bd8420945b953e1b806041bea4d72a3943d86 Reviewed-on: http://gerrit.cloudera.org:8080/3779 Reviewed-by: Dan Hecht <dhecht@cloudera.com> Tested-by: Internal Jenkins
68 lines
3.0 KiB
Python
68 lines
3.0 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.
|
|
|
|
# Validates table stored on the LocalFileSystem.
|
|
#
|
|
import pytest
|
|
from subprocess import check_call, call
|
|
|
|
from tests.common.impala_test_suite import ImpalaTestSuite
|
|
from tests.common.skip import SkipIf
|
|
from tests.common.test_dimensions import create_single_exec_option_dimension
|
|
from tests.util.filesystem_utils import get_secondary_fs_path
|
|
|
|
@SkipIf.no_secondary_fs
|
|
class TestMultipleFilesystems(ImpalaTestSuite):
|
|
"""
|
|
Tests that tables and queries can span multiple filesystems.
|
|
"""
|
|
|
|
@classmethod
|
|
def get_workload(self):
|
|
return 'functional-query'
|
|
|
|
@classmethod
|
|
def add_test_dimensions(cls):
|
|
super(TestMultipleFilesystems, cls).add_test_dimensions()
|
|
cls.TestMatrix.add_dimension(create_single_exec_option_dimension())
|
|
|
|
cls.TestMatrix.add_constraint(lambda v:\
|
|
v.get_value('table_format').file_format == 'text' and \
|
|
v.get_value('table_format').compression_codec == 'none')
|
|
|
|
def _populate_secondary_fs_partitions(self, db_name):
|
|
# This directory may already exist. So we needn't mind if this call fails.
|
|
call(["hadoop", "fs", "-mkdir", get_secondary_fs_path("/multi_fs_tests/")], shell=False)
|
|
check_call(["hadoop", "fs", "-mkdir",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % db_name)], shell=False)
|
|
check_call(["hadoop", "fs", "-cp", "/test-warehouse/alltypes_parquet/",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % db_name)], shell=False)
|
|
check_call(["hadoop", "fs", "-cp", "/test-warehouse/tinytable/",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % db_name)], shell=False)
|
|
|
|
@pytest.mark.execute_serially
|
|
def test_multiple_filesystems(self, vector, unique_database):
|
|
try:
|
|
self._populate_secondary_fs_partitions(unique_database)
|
|
self.run_test_case('QueryTest/multiple-filesystems', vector, use_db=unique_database)
|
|
finally:
|
|
# We delete this from the secondary filesystem here because the database was created
|
|
# in HDFS but the queries will create this path in the secondary FS as well. So
|
|
# dropping the database will not delete the directory in the secondary FS.
|
|
check_call(["hadoop", "fs", "-rm", "-r",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % unique_database)], shell=False)
|