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

92 lines
2.9 KiB
Python
Raw Normal View History

#
# 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.
#
import sys
from pyspark import since, _NoValue
[SPARK-23698][PYTHON] Resolve undefined names in Python 3 ## What changes were proposed in this pull request? Fix issues arising from the fact that builtins __file__, __long__, __raw_input()__, __unicode__, __xrange()__, etc. were all removed from Python 3. __Undefined names__ have the potential to raise [NameError](https://docs.python.org/3/library/exceptions.html#NameError) at runtime. ## How was this patch tested? * $ __python2 -m flake8 . --count --select=E9,F82 --show-source --statistics__ * $ __python3 -m flake8 . --count --select=E9,F82 --show-source --statistics__ holdenk flake8 testing of https://github.com/apache/spark on Python 3.6.3 $ __python3 -m flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics__ ``` ./dev/merge_spark_pr.py:98:14: F821 undefined name 'raw_input' result = raw_input("\n%s (y/n): " % prompt) ^ ./dev/merge_spark_pr.py:136:22: F821 undefined name 'raw_input' primary_author = raw_input( ^ ./dev/merge_spark_pr.py:186:16: F821 undefined name 'raw_input' pick_ref = raw_input("Enter a branch name [%s]: " % default_branch) ^ ./dev/merge_spark_pr.py:233:15: F821 undefined name 'raw_input' jira_id = raw_input("Enter a JIRA id [%s]: " % default_jira_id) ^ ./dev/merge_spark_pr.py:278:20: F821 undefined name 'raw_input' fix_versions = raw_input("Enter comma-separated fix version(s) [%s]: " % default_fix_versions) ^ ./dev/merge_spark_pr.py:317:28: F821 undefined name 'raw_input' raw_assignee = raw_input( ^ ./dev/merge_spark_pr.py:430:14: F821 undefined name 'raw_input' pr_num = raw_input("Which pull request would you like to merge? (e.g. 34): ") ^ ./dev/merge_spark_pr.py:442:18: F821 undefined name 'raw_input' result = raw_input("Would you like to use the modified title? (y/n): ") ^ ./dev/merge_spark_pr.py:493:11: F821 undefined name 'raw_input' while raw_input("\n%s (y/n): " % pick_prompt).lower() == "y": ^ ./dev/create-release/releaseutils.py:58:16: F821 undefined name 'raw_input' response = raw_input("%s [y/n]: " % msg) ^ ./dev/create-release/releaseutils.py:152:38: F821 undefined name 'unicode' author = unidecode.unidecode(unicode(author, "UTF-8")).strip() ^ ./python/setup.py:37:11: F821 undefined name '__version__' VERSION = __version__ ^ ./python/pyspark/cloudpickle.py:275:18: F821 undefined name 'buffer' dispatch[buffer] = save_buffer ^ ./python/pyspark/cloudpickle.py:807:18: F821 undefined name 'file' dispatch[file] = save_file ^ ./python/pyspark/sql/conf.py:61:61: F821 undefined name 'unicode' if not isinstance(obj, str) and not isinstance(obj, unicode): ^ ./python/pyspark/sql/streaming.py:25:21: F821 undefined name 'long' intlike = (int, long) ^ ./python/pyspark/streaming/dstream.py:405:35: F821 undefined name 'long' return self._sc._jvm.Time(long(timestamp * 1000)) ^ ./sql/hive/src/test/resources/data/scripts/dumpdata_script.py:21:10: F821 undefined name 'xrange' for i in xrange(50): ^ ./sql/hive/src/test/resources/data/scripts/dumpdata_script.py:22:14: F821 undefined name 'xrange' for j in xrange(5): ^ ./sql/hive/src/test/resources/data/scripts/dumpdata_script.py:23:18: F821 undefined name 'xrange' for k in xrange(20022): ^ 20 F821 undefined name 'raw_input' 20 ``` Closes #20838 from cclauss/fix-undefined-names. Authored-by: cclauss <cclauss@bluewin.ch> Signed-off-by: Bryan Cutler <cutlerb@gmail.com>
2018-08-22 13:06:59 -04:00
class RuntimeConfig(object):
"""User-facing configuration API, accessible through `SparkSession.conf`.
Options set here are automatically propagated to the Hadoop configuration during I/O.
"""
def __init__(self, jconf):
"""Create a new RuntimeConfig that wraps the underlying JVM object."""
self._jconf = jconf
@since(2.0)
def set(self, key, value):
"""Sets the given Spark runtime configuration property."""
self._jconf.set(key, value)
@since(2.0)
def get(self, key, default=_NoValue):
"""Returns the value of Spark runtime configuration property for the given key,
assuming it is set.
"""
self._checkType(key, "key")
if default is _NoValue:
return self._jconf.get(key)
else:
if default is not None:
self._checkType(default, "default")
return self._jconf.get(key, default)
@since(2.0)
def unset(self, key):
"""Resets the configuration property for the given key."""
self._jconf.unset(key)
def _checkType(self, obj, identifier):
"""Assert that an object is of type str."""
if not isinstance(obj, str):
raise TypeError("expected %s '%s' to be a string (was '%s')" %
(identifier, obj, type(obj).__name__))
@since(2.4)
def isModifiable(self, key):
"""Indicates whether the configuration property with the given key
is modifiable in the current session.
"""
return self._jconf.isModifiable(key)
def _test():
import os
import doctest
from pyspark.sql.session import SparkSession
import pyspark.sql.conf
os.chdir(os.environ["SPARK_HOME"])
globs = pyspark.sql.conf.__dict__.copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("sql.conf tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
globs['spark'] = spark
(failure_count, test_count) = doctest.testmod(pyspark.sql.conf, globs=globs)
spark.stop()
if failure_count:
sys.exit(-1)
if __name__ == "__main__":
_test()