spark-instrumented-optimizer/python/pyspark/conf.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

183 lines
6 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.
#
"""
>>> from pyspark.conf import SparkConf
>>> from pyspark.context import SparkContext
>>> conf = SparkConf()
>>> conf.setMaster("local").setAppName("My app")
<pyspark.conf.SparkConf object at ...>
>>> conf.get("spark.master")
u'local'
>>> conf.get("spark.app.name")
u'My app'
>>> sc = SparkContext(conf=conf)
>>> sc.master
u'local'
>>> sc.appName
u'My app'
>>> sc.sparkHome is None
True
>>> conf = SparkConf(loadDefaults=False)
>>> conf.setSparkHome("/path")
<pyspark.conf.SparkConf object at ...>
>>> conf.get("spark.home")
u'/path'
>>> conf.setExecutorEnv("VAR1", "value1")
<pyspark.conf.SparkConf object at ...>
>>> conf.setExecutorEnv(pairs = [("VAR3", "value3"), ("VAR4", "value4")])
<pyspark.conf.SparkConf object at ...>
>>> conf.get("spark.executorEnv.VAR1")
u'value1'
>>> print conf.toDebugString()
spark.executorEnv.VAR1=value1
spark.executorEnv.VAR3=value3
spark.executorEnv.VAR4=value4
spark.home=/path
>>> sorted(conf.getAll(), key=lambda p: p[0])
[(u'spark.executorEnv.VAR1', u'value1'), (u'spark.executorEnv.VAR3', u'value3'), \
(u'spark.executorEnv.VAR4', u'value4'), (u'spark.home', u'/path')]
"""
class SparkConf(object):
"""
Configuration for a Spark application. Used to set various Spark
parameters as key-value pairs.
Most of the time, you would create a SparkConf object with
C{SparkConf()}, which will load values from C{spark.*} Java system
properties as well. In this case, any parameters you set directly on
the C{SparkConf} object take priority over system properties.
For unit tests, you can also call C{SparkConf(false)} to skip
loading external settings and get the same configuration no matter
what the system properties are.
All setter methods in this class support chaining. For example,
you can write C{conf.setMaster("local").setAppName("My app")}.
Note that once a SparkConf object is passed to Spark, it is cloned
and can no longer be modified by the user.
"""
def __init__(self, loadDefaults=True, _jvm=None, _jconf=None):
"""
Create a new Spark configuration.
@param loadDefaults: whether to load values from Java system
properties (True by default)
@param _jvm: internal parameter used to pass a handle to the
Java VM; does not need to be set by users
@param _jconf: Optionally pass in an existing SparkConf handle
to use its parameters
"""
if _jconf:
self._jconf = _jconf
else:
from pyspark.context import SparkContext
SparkContext._ensure_initialized()
_jvm = _jvm or SparkContext._jvm
self._jconf = _jvm.SparkConf(loadDefaults)
def set(self, key, value):
"""Set a configuration property."""
self._jconf.set(key, unicode(value))
return self
def setIfMissing(self, key, value):
"""Set a configuration property, if not already set."""
if self.get(key) is None:
self.set(key, value)
return self
def setMaster(self, value):
"""Set master URL to connect to."""
self._jconf.setMaster(value)
return self
def setAppName(self, value):
"""Set application name."""
self._jconf.setAppName(value)
return self
def setSparkHome(self, value):
"""Set path where Spark is installed on worker nodes."""
self._jconf.setSparkHome(value)
return self
def setExecutorEnv(self, key=None, value=None, pairs=None):
"""Set an environment variable to be passed to executors."""
if (key is not None and pairs is not None) or (key is None and pairs is None):
raise Exception("Either pass one key-value pair or a list of pairs")
elif key is not None:
self._jconf.setExecutorEnv(key, value)
elif pairs is not None:
for (k, v) in pairs:
self._jconf.setExecutorEnv(k, v)
return self
def setAll(self, pairs):
"""
Set multiple parameters, passed as a list of key-value pairs.
@param pairs: list of key-value pairs to set
"""
for (k, v) in pairs:
self._jconf.set(k, v)
return self
def get(self, key, defaultValue=None):
"""Get the configured value for some key, or return a default otherwise."""
if defaultValue is None: # Py4J doesn't call the right get() if we pass None
if not self._jconf.contains(key):
return None
return self._jconf.get(key)
else:
return self._jconf.get(key, defaultValue)
def getAll(self):
"""Get all values as a list of key-value pairs."""
pairs = []
for elem in self._jconf.getAll():
pairs.append((elem._1(), elem._2()))
return pairs
def contains(self, key):
"""Does this configuration contain a given key?"""
return self._jconf.contains(key)
def toDebugString(self):
"""
Returns a printable version of the configuration, as a list of
key=value pairs, one per line.
"""
return self._jconf.toDebugString()
def _test():
import doctest
(failure_count, test_count) = doctest.testmod(optionflags=doctest.ELLIPSIS)
if failure_count:
exit(-1)
if __name__ == "__main__":
_test()