From 10d04213ffda9c64b7e39c7debc433be8ea343c7 Mon Sep 17 00:00:00 2001
From: Michael Armbrust <michael@databricks.com>
Date: Sat, 19 Apr 2014 15:08:54 -0700
Subject: [PATCH] Add insertInto and saveAsTable to Python API.
Author: Michael Armbrust <michael@databricks.com>
Closes #447 from marmbrus/pythonInsert and squashes the following commits:
c7ab692 [Michael Armbrust] Keep docstrings < 72 chars.
ff62870 [Michael Armbrust] Add insertInto and saveAsTable to Python API.
---
python/pyspark/sql.py | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py
index 27753d5ba5..114fa138d0 100644
--- a/python/pyspark/sql.py
+++ b/python/pyspark/sql.py
@@ -305,6 +305,19 @@ class SchemaRDD(RDD):
"""
self._jschema_rdd.registerAsTable(name)
+ def insertInto(self, tableName, overwrite = False):
+ """
+ Inserts the contents of this SchemaRDD into the specified table,
+ optionally overwriting any existing data.
+ """
+ self._jschema_rdd.insertInto(tableName, overwrite)
+
+ def saveAsTable(self, tableName):
+ """
+ Creates a new table with the contents of this SchemaRDD.
+ """
+ self._jschema_rdd.saveAsTable(tableName)
+
def _toPython(self):
# We have to import the Row class explicitly, so that the reference Pickler has is
# pyspark.sql.Row instead of __main__.Row
--
GitLab