diff options
author | Nicholas Chammas <nicholas.chammas@gmail.com> | 2014-08-06 12:58:24 -0700 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2014-08-06 12:58:24 -0700 |
commit | d614967b0bad1e6c5277d612602ec0a653a00258 (patch) | |
tree | 8df1a52cbe074af4f928c0ac8f08a63075882d0b /python/pyspark/context.py | |
parent | a6cd31108f0d73ce6823daafe8447677e03cfd13 (diff) | |
download | spark-d614967b0bad1e6c5277d612602ec0a653a00258.tar.gz spark-d614967b0bad1e6c5277d612602ec0a653a00258.tar.bz2 spark-d614967b0bad1e6c5277d612602ec0a653a00258.zip |
[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
Diffstat (limited to 'python/pyspark/context.py')
-rw-r--r-- | python/pyspark/context.py | 25 |
1 files changed, 14 insertions, 11 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py index 2e80eb50f2..4001ecab5e 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -47,6 +47,7 @@ DEFAULT_CONFIGS = { class SparkContext(object): + """ Main entry point for Spark functionality. A SparkContext represents the connection to a Spark cluster, and can be used to create L{RDD}s and @@ -213,7 +214,7 @@ class SparkContext(object): if instance: if (SparkContext._active_spark_context and - SparkContext._active_spark_context != instance): + SparkContext._active_spark_context != instance): currentMaster = SparkContext._active_spark_context.master currentAppName = SparkContext._active_spark_context.appName callsite = SparkContext._active_spark_context._callsite @@ -406,7 +407,7 @@ class SparkContext(object): batchSize = max(1, batchSize or self._default_batch_size_for_serialized_input) ser = BatchedSerializer(PickleSerializer()) if (batchSize > 1) else PickleSerializer() jrdd = self._jvm.PythonRDD.sequenceFile(self._jsc, path, keyClass, valueClass, - keyConverter, valueConverter, minSplits, batchSize) + keyConverter, valueConverter, minSplits, batchSize) return RDD(jrdd, self, ser) def newAPIHadoopFile(self, path, inputFormatClass, keyClass, valueClass, keyConverter=None, @@ -437,7 +438,8 @@ class SparkContext(object): batchSize = max(1, batchSize or self._default_batch_size_for_serialized_input) ser = BatchedSerializer(PickleSerializer()) if (batchSize > 1) else PickleSerializer() jrdd = self._jvm.PythonRDD.newAPIHadoopFile(self._jsc, path, inputFormatClass, keyClass, - valueClass, keyConverter, valueConverter, jconf, batchSize) + valueClass, keyConverter, valueConverter, + jconf, batchSize) return RDD(jrdd, self, ser) def newAPIHadoopRDD(self, inputFormatClass, keyClass, valueClass, keyConverter=None, @@ -465,7 +467,8 @@ class SparkContext(object): batchSize = max(1, batchSize or self._default_batch_size_for_serialized_input) ser = BatchedSerializer(PickleSerializer()) if (batchSize > 1) else PickleSerializer() jrdd = self._jvm.PythonRDD.newAPIHadoopRDD(self._jsc, inputFormatClass, keyClass, - valueClass, keyConverter, valueConverter, jconf, batchSize) + valueClass, keyConverter, valueConverter, + jconf, batchSize) return RDD(jrdd, self, ser) def hadoopFile(self, path, inputFormatClass, keyClass, valueClass, keyConverter=None, @@ -496,7 +499,8 @@ class SparkContext(object): batchSize = max(1, batchSize or self._default_batch_size_for_serialized_input) ser = BatchedSerializer(PickleSerializer()) if (batchSize > 1) else PickleSerializer() jrdd = self._jvm.PythonRDD.hadoopFile(self._jsc, path, inputFormatClass, keyClass, - valueClass, keyConverter, valueConverter, jconf, batchSize) + valueClass, keyConverter, valueConverter, + jconf, batchSize) return RDD(jrdd, self, ser) def hadoopRDD(self, inputFormatClass, keyClass, valueClass, keyConverter=None, @@ -523,8 +527,9 @@ class SparkContext(object): jconf = self._dictToJavaMap(conf) batchSize = max(1, batchSize or self._default_batch_size_for_serialized_input) ser = BatchedSerializer(PickleSerializer()) if (batchSize > 1) else PickleSerializer() - jrdd = self._jvm.PythonRDD.hadoopRDD(self._jsc, inputFormatClass, keyClass, valueClass, - keyConverter, valueConverter, jconf, batchSize) + jrdd = self._jvm.PythonRDD.hadoopRDD(self._jsc, inputFormatClass, keyClass, + valueClass, keyConverter, valueConverter, + jconf, batchSize) return RDD(jrdd, self, ser) def _checkpointFile(self, name, input_deserializer): @@ -555,8 +560,7 @@ class SparkContext(object): first = rdds[0]._jrdd rest = [x._jrdd for x in rdds[1:]] rest = ListConverter().convert(rest, self._gateway._gateway_client) - return RDD(self._jsc.union(first, rest), self, - rdds[0]._jrdd_deserializer) + return RDD(self._jsc.union(first, rest), self, rdds[0]._jrdd_deserializer) def broadcast(self, value): """ @@ -568,8 +572,7 @@ class SparkContext(object): pickleSer = PickleSerializer() pickled = pickleSer.dumps(value) jbroadcast = self._jsc.broadcast(bytearray(pickled)) - return Broadcast(jbroadcast.id(), value, jbroadcast, - self._pickled_broadcast_vars) + return Broadcast(jbroadcast.id(), value, jbroadcast, self._pickled_broadcast_vars) def accumulator(self, value, accum_param=None): """ |