[SPARK-11114][PYSPARK] add getOrCreate for SparkContext/SQLContext in Python

Also added SQLContext.newSession()

Author: Davies Liu <davies@databricks.com>

Closes #9122 from davies/py_create.

1 files changed, 14 insertions, 2 deletions

diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index 4969d85f52..afd74d937a 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -21,7 +21,7 @@ import os
 import shutil
 import signal
 import sys
-from threading import Lock
+from threading import RLock
 from tempfile import NamedTemporaryFile
 
 from pyspark import accumulators
@@ -65,7 +65,7 @@ class SparkContext(object):
     _jvm = None
     _next_accum_id = 0
     _active_spark_context = None
-    _lock = Lock()
+    _lock = RLock()
     _python_includes = None  # zip and egg files that need to be added to PYTHONPATH
 
     PACKAGE_EXTENSIONS = ('.zip', '.egg', '.jar')
@@ -280,6 +280,18 @@ class SparkContext(object):
         """
         self.stop()
 
+    @classmethod
+    def getOrCreate(cls, conf=None):
+        """
+        Get or instantiate a SparkContext and register it as a singleton object.
+
+        :param conf: SparkConf (optional)
+        """
+        with SparkContext._lock:
+            if SparkContext._active_spark_context is None:
+                SparkContext(conf=conf or SparkConf())
+            return SparkContext._active_spark_context
+
     def setLogLevel(self, logLevel):
         """
         Control our logLevel. This overrides any user-defined log settings.