spark-instrumented-optimizer/python/pyspark/storagelevel.py
Nicholas Chammas d614967b0b [SPARK-2627] [PySpark] have the build enforce PEP 8 automatically
As described in [SPARK-2627](https://issues.apache.org/jira/browse/SPARK-2627), we'd like Python code to automatically be checked for PEP 8 compliance by Jenkins. This pull request aims to do that.

Notes:
* We may need to install [`pep8`](https://pypi.python.org/pypi/pep8) on the build server.
* I'm expecting tests to fail now that PEP 8 compliance is being checked as part of the build. I'm fine with cleaning up any remaining PEP 8 violations as part of this pull request.
* I did not understand why the RAT and scalastyle reports are saved to text files. I did the same for the PEP 8 check, but only so that the console output style can match those for the RAT and scalastyle checks. The PEP 8 report is removed right after the check is complete.
* Updates to the ["Contributing to Spark"](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark) guide will be submitted elsewhere, as I don't believe that text is part of the Spark repo.

Author: Nicholas Chammas <nicholas.chammas@gmail.com>
Author: nchammas <nicholas.chammas@gmail.com>

Closes #1744 from nchammas/master and squashes the following commits:

274b238 [Nicholas Chammas] [SPARK-2627] [PySpark] minor indentation changes
983d963 [nchammas] Merge pull request #5 from apache/master
1db5314 [nchammas] Merge pull request #4 from apache/master
0e0245f [Nicholas Chammas] [SPARK-2627] undo erroneous whitespace fixes
bf30942 [Nicholas Chammas] [SPARK-2627] PEP8: comment spacing
6db9a44 [nchammas] Merge pull request #3 from apache/master
7b4750e [Nicholas Chammas] merge upstream changes
91b7584 [Nicholas Chammas] [SPARK-2627] undo unnecessary line breaks
44e3e56 [Nicholas Chammas] [SPARK-2627] use tox.ini to exclude files
b09fae2 [Nicholas Chammas] don't wrap comments unnecessarily
bfb9f9f [Nicholas Chammas] [SPARK-2627] keep up with the PEP 8 fixes
9da347f [nchammas] Merge pull request #2 from apache/master
aa5b4b5 [Nicholas Chammas] [SPARK-2627] follow Spark bash style for if blocks
d0a83b9 [Nicholas Chammas] [SPARK-2627] check that pep8 downloaded fine
dffb5dd [Nicholas Chammas] [SPARK-2627] download pep8 at runtime
a1ce7ae [Nicholas Chammas] [SPARK-2627] space out test report sections
21da538 [Nicholas Chammas] [SPARK-2627] it's PEP 8, not PEP8
6f4900b [Nicholas Chammas] [SPARK-2627] more misc PEP 8 fixes
fe57ed0 [Nicholas Chammas] removing merge conflict backups
9c01d4c [nchammas] Merge pull request #1 from apache/master
9a66cb0 [Nicholas Chammas] resolving merge conflicts
a31ccc4 [Nicholas Chammas] [SPARK-2627] miscellaneous PEP 8 fixes
beaa9ac [Nicholas Chammas] [SPARK-2627] fail check on non-zero status
723ed39 [Nicholas Chammas] always delete the report file
0541ebb [Nicholas Chammas] [SPARK-2627] call Python linter from run-tests
12440fa [Nicholas Chammas] [SPARK-2627] add Scala linter
61c07b9 [Nicholas Chammas] [SPARK-2627] add Python linter
75ad552 [Nicholas Chammas] make check output style consistent
2014-08-06 12:58:24 -07:00

61 lines
2.7 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.
#
__all__ = ["StorageLevel"]
class StorageLevel:
"""
Flags for controlling the storage of an RDD. Each StorageLevel records whether to use memory,
whether to drop the RDD to disk if it falls out of memory, whether to keep the data in memory
in a serialized format, and whether to replicate the RDD partitions on multiple nodes.
Also contains static constants for some commonly used storage levels, such as MEMORY_ONLY.
"""
def __init__(self, useDisk, useMemory, useOffHeap, deserialized, replication=1):
self.useDisk = useDisk
self.useMemory = useMemory
self.useOffHeap = useOffHeap
self.deserialized = deserialized
self.replication = replication
def __repr__(self):
return "StorageLevel(%s, %s, %s, %s, %s)" % (
self.useDisk, self.useMemory, self.useOffHeap, self.deserialized, self.replication)
def __str__(self):
result = ""
result += "Disk " if self.useDisk else ""
result += "Memory " if self.useMemory else ""
result += "Tachyon " if self.useOffHeap else ""
result += "Deserialized " if self.deserialized else "Serialized "
result += "%sx Replicated" % self.replication
return result
StorageLevel.DISK_ONLY = StorageLevel(True, False, False, False)
StorageLevel.DISK_ONLY_2 = StorageLevel(True, False, False, False, 2)
StorageLevel.MEMORY_ONLY = StorageLevel(False, True, False, True)
StorageLevel.MEMORY_ONLY_2 = StorageLevel(False, True, False, True, 2)
StorageLevel.MEMORY_ONLY_SER = StorageLevel(False, True, False, False)
StorageLevel.MEMORY_ONLY_SER_2 = StorageLevel(False, True, False, False, 2)
StorageLevel.MEMORY_AND_DISK = StorageLevel(True, True, False, True)
StorageLevel.MEMORY_AND_DISK_2 = StorageLevel(True, True, False, True, 2)
StorageLevel.MEMORY_AND_DISK_SER = StorageLevel(True, True, False, False)
StorageLevel.MEMORY_AND_DISK_SER_2 = StorageLevel(True, True, False, False, 2)
StorageLevel.OFF_HEAP = StorageLevel(False, False, True, False, 1)