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
55 lines
2.0 KiB
Python
Executable File
55 lines
2.0 KiB
Python
Executable File
#!/usr/bin/env 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.
|
|
|
|
'''This is a mapper for use with hadoop streaming. See data_generator.DatabasePopulator
|
|
for more information on how this file is used.
|
|
'''
|
|
|
|
import os
|
|
import random
|
|
import sys
|
|
|
|
# When running locally, the PYTHONPATH needed by impala-shell interferes with python
|
|
# through YARN. Specifically, when the data generator needs to import common.py, python
|
|
# looks at $IMPALA_HOME/tests/common and errors when it doesn't find what was asked for.
|
|
sys.path.insert(1, os.getcwd())
|
|
|
|
from data_generator_mapred_common import (
|
|
deserialize,
|
|
estimate_rows_per_reducer,
|
|
MB_PER_REDUCER,
|
|
serialize)
|
|
|
|
for line in sys.stdin:
|
|
table_data_generator = deserialize(line)
|
|
random.seed(table_data_generator.randomization_seed)
|
|
row_count = table_data_generator.row_count
|
|
rows_per_batch = estimate_rows_per_reducer(table_data_generator, MB_PER_REDUCER)
|
|
batch_idx = 0
|
|
while row_count > 0:
|
|
table_data_generator.row_count = min(row_count, rows_per_batch)
|
|
table_data_generator.randomization_seed = int(random.random() * sys.maxint)
|
|
|
|
# Generate input for the reducers.
|
|
print("%s\t%s\t%s" % (table_data_generator.table.name, batch_idx,
|
|
serialize(table_data_generator)))
|
|
|
|
batch_idx += 1
|
|
row_count -= rows_per_batch
|