From de9c85ccaacd12de9837eb88eae0a7e7ededd679 Mon Sep 17 00:00:00 2001 From: Sandeep Singh <sandeep@techaddict.me> Date: Wed, 11 May 2016 14:15:18 -0700 Subject: [PATCH] [SPARK-15270] [SQL] Use SparkSession Builder to build a session with HiveSupport ## What changes were proposed in this pull request? Before: Creating a hiveContext was failing ```python from pyspark.sql import HiveContext hc = HiveContext(sc) ``` with ``` Traceback (most recent call last): File "<stdin>", line 1, in <module> File "spark-2.0/python/pyspark/sql/context.py", line 458, in __init__ sparkSession = SparkSession.withHiveSupport(sparkContext) File "spark-2.0/python/pyspark/sql/session.py", line 192, in withHiveSupport jsparkSession = sparkContext._jvm.SparkSession.withHiveSupport(sparkContext._jsc.sc()) File "spark-2.0/python/lib/py4j-0.9.2-src.zip/py4j/java_gateway.py", line 1048, in __getattr__ py4j.protocol.Py4JError: org.apache.spark.sql.SparkSession.withHiveSupport does not exist in the JVM ``` Now: ```python >>> from pyspark.sql import HiveContext >>> hc = HiveContext(sc) >>> hc.range(0, 100) DataFrame[id: bigint] >>> hc.range(0, 100).count() 100 ``` ## How was this patch tested? Existing Tests, tested manually in python shell Author: Sandeep Singh <sandeep@techaddict.me> Closes #13056 from techaddict/SPARK-15270. --- python/pyspark/sql/context.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py index 78ab2e81bf..02e742c124 100644 --- a/python/pyspark/sql/context.py +++ b/python/pyspark/sql/context.py @@ -455,7 +455,7 @@ class HiveContext(SQLContext): def __init__(self, sparkContext, jhiveContext=None): if jhiveContext is None: - sparkSession = SparkSession.withHiveSupport(sparkContext) + sparkSession = SparkSession.builder.enableHiveSupport().getOrCreate() else: sparkSession = SparkSession(sparkContext, jhiveContext.sparkSession()) SQLContext.__init__(self, sparkContext, sparkSession, jhiveContext) -- GitLab