[SPARK-5872] [SQL] create a sqlCtx in pyspark shell

The sqlCtx will be HiveContext if hive is built in assembly jar, or SQLContext if not.

It also skip the Hive tests in pyspark.sql.tests if no hive is available.

Author: Davies Liu <davies@databricks.com>

Closes #4659 from davies/sqlctx and squashes the following commits:

0e6629a [Davies Liu] sqlCtx in pyspark

1 files changed, 12 insertions, 1 deletions

diff --git a/python/pyspark/shell.py b/python/pyspark/shell.py
index 4cf4b89ccf..1a02fece9c 100644
--- a/python/pyspark/shell.py
+++ b/python/pyspark/shell.py
@@ -31,8 +31,12 @@ if sys.version_info[0] != 2:
 import atexit
 import os
 import platform
+
+import py4j
+
 import pyspark
 from pyspark.context import SparkContext
+from pyspark.sql import SQLContext, HiveContext
 from pyspark.storagelevel import StorageLevel
 
 # this is the deprecated equivalent of ADD_JARS
@@ -46,6 +50,13 @@ if os.environ.get("SPARK_EXECUTOR_URI"):
 sc = SparkContext(appName="PySparkShell", pyFiles=add_files)
 atexit.register(lambda: sc.stop())
 
+try:
+    # Try to access HiveConf, it will raise exception if Hive is not added
+    sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
+    sqlCtx = HiveContext(sc)
+except py4j.protocol.Py4JError:
+    sqlCtx = SQLContext(sc)
+
 print("""Welcome to
       ____              __
      / __/__  ___ _____/ /__
@@ -57,7 +68,7 @@ print("Using Python version %s (%s, %s)" % (
     platform.python_version(),
     platform.python_build()[0],
     platform.python_build()[1]))
-print("SparkContext available as sc.")
+print("SparkContext available as sc, %s available as sqlCtx." % sqlCtx.__class__.__name__)
 
 if add_files is not None:
     print("Warning: ADD_FILES environment variable is deprecated, use --py-files argument instead")