diff options
author | Davies Liu <davies@databricks.com> | 2015-05-23 09:07:14 -0700 |
---|---|---|
committer | Davies Liu <davies@databricks.com> | 2015-05-23 09:07:14 -0700 |
commit | be47af1bdba469f84775c2b5936f8cb956c7c02b (patch) | |
tree | 3c4016d27ad15f908ae5e0307180189347df6247 /python/pyspark/sql | |
parent | efe3bfdf496aa6206ace2697e31dd4c0c3c824fb (diff) | |
download | spark-be47af1bdba469f84775c2b5936f8cb956c7c02b.tar.gz spark-be47af1bdba469f84775c2b5936f8cb956c7c02b.tar.bz2 spark-be47af1bdba469f84775c2b5936f8cb956c7c02b.zip |
[SPARK-7840] add insertInto() to Writer
Add tests later.
Author: Davies Liu <davies@databricks.com>
Closes #6375 from davies/insertInto and squashes the following commits:
826423e [Davies Liu] add insertInto() to Writer
Diffstat (limited to 'python/pyspark/sql')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 2 | ||||
-rw-r--r-- | python/pyspark/sql/readwriter.py | 22 |
2 files changed, 16 insertions, 8 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 55cad8238e..936487519a 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): diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py index 02b3aab2b1..b6fd413bec 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. |