You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by da...@apache.org on 2015/05/23 18:07:32 UTC
spark git commit: [SPARK-7840] add insertInto() to Writer
Repository: spark
Updated Branches:
refs/heads/master efe3bfdf4 -> be47af1bd
[SPARK-7840] add insertInto() to Writer
Add tests later.
Author: Davies Liu <da...@databricks.com>
Closes #6375 from davies/insertInto and squashes the following commits:
826423e [Davies Liu] add insertInto() to Writer
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/be47af1b
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/be47af1b
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/be47af1b
Branch: refs/heads/master
Commit: be47af1bdba469f84775c2b5936f8cb956c7c02b
Parents: efe3bfd
Author: Davies Liu <da...@databricks.com>
Authored: Sat May 23 09:07:14 2015 -0700
Committer: Davies Liu <da...@databricks.com>
Committed: Sat May 23 09:07:14 2015 -0700
----------------------------------------------------------------------
python/pyspark/sql/dataframe.py | 2 +-
python/pyspark/sql/readwriter.py | 22 +++++++++++++++-------
2 files changed, 16 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/be47af1b/python/pyspark/sql/dataframe.py
----------------------------------------------------------------------
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 55cad82..9364875 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -163,7 +163,7 @@ class DataFrame(object):
Optionally overwriting any existing data.
"""
- self._jdf.insertInto(tableName, overwrite)
+ self.write.insertInto(tableName, overwrite)
@since(1.3)
def saveAsTable(self, tableName, source=None, mode="error", **options):
http://git-wip-us.apache.org/repos/asf/spark/blob/be47af1b/python/pyspark/sql/readwriter.py
----------------------------------------------------------------------
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py
index 02b3aab..b6fd413 100644
--- a/python/pyspark/sql/readwriter.py
+++ b/python/pyspark/sql/readwriter.py
@@ -226,17 +226,25 @@ class DataFrameWriter(object):
else:
jwrite.save(path)
+ def insertInto(self, tableName, overwrite=False):
+ """
+ Inserts the content of the :class:`DataFrame` to the specified table.
+ It requires that the schema of the class:`DataFrame` is the same as the
+ schema of the table.
+
+ Optionally overwriting any existing data.
+ """
+ self._jwrite.mode("overwrite" if overwrite else "append").insertInto(tableName)
+
@since(1.4)
def saveAsTable(self, name, format=None, mode="error", **options):
"""
- Saves the contents of this :class:`DataFrame` to a data source as a table.
-
- The data source is specified by the ``source`` and a set of ``options``.
- If ``source`` is not specified, the default data source configured by
- ``spark.sql.sources.default`` will be used.
+ Saves the content of the :class:`DataFrame` as the specified table.
- Additionally, mode is used to specify the behavior of the saveAsTable operation when
- table already exists in the data source. There are four modes:
+ In the case the table already exists, behavior of this function depends on the
+ save mode, specified by the `mode` function (default to throwing an exception).
+ When `mode` is `Overwrite`, the schema of the [[DataFrame]] does not need to be
+ the same as that of the existing table.
* `append`: Append contents of this :class:`DataFrame` to existing data.
* `overwrite`: Overwrite existing data.
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org