You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2014/04/20 00:09:00 UTC
git commit: Add insertInto and saveAsTable to Python API.
Repository: spark
Updated Branches:
refs/heads/master 5d0f58b2e -> 10d04213f
Add insertInto and saveAsTable to Python API.
Author: Michael Armbrust <mi...@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.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/10d04213
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/10d04213
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/10d04213
Branch: refs/heads/master
Commit: 10d04213ffda9c64b7e39c7debc433be8ea343c7
Parents: 5d0f58b
Author: Michael Armbrust <mi...@databricks.com>
Authored: Sat Apr 19 15:08:54 2014 -0700
Committer: Matei Zaharia <ma...@databricks.com>
Committed: Sat Apr 19 15:08:54 2014 -0700
----------------------------------------------------------------------
python/pyspark/sql.py | 13 +++++++++++++
1 file changed, 13 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/10d04213/python/pyspark/sql.py
----------------------------------------------------------------------
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py
index 27753d5..114fa13 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