diff options
| author | Cheolsoo Park <cheolsoop@netflix.com> | 2015-06-29 00:13:39 -0700 |
|---|---|---|
| committer | Reynold Xin <rxin@databricks.com> | 2015-06-29 00:21:31 -0700 |
| commit | 9d9c4b476d194f8f0102c4bf0fc263de9d1fb3be (patch) | |
| tree | f3172a87730cb47ddb1fc1725ff1432f82f1bc52 | |
| parent | e1bbf1a080296e4d3d692379f06b7db0d0629573 (diff) | |
| download | spark-9d9c4b476d194f8f0102c4bf0fc263de9d1fb3be.tar.gz spark-9d9c4b476d194f8f0102c4bf0fc263de9d1fb3be.tar.bz2 spark-9d9c4b476d194f8f0102c4bf0fc263de9d1fb3be.zip | |
[SPARK-8355] [SQL] Python DataFrameReader/Writer should mirror Scala
I compared PySpark DataFrameReader/Writer against Scala ones. `Option` function is missing in both reader and writer, but the rest seems to all match.
I added `Option` to reader and writer and updated the `pyspark-sql` test.
Author: Cheolsoo Park <cheolsoop@netflix.com>
Closes #7078 from piaozhexiu/SPARK-8355 and squashes the following commits:
c63d419 [Cheolsoo Park] Fix version
524e0aa [Cheolsoo Park] Add option function to df reader and writer
(cherry picked from commit ac2e17b01c0843d928a363d2cc4faf57ec8c8b47)
Signed-off-by: Reynold Xin <rxin@databricks.com>
| -rw-r--r-- | python/pyspark/sql/readwriter.py | 14 | ||||
| -rw-r--r-- | python/pyspark/sql/tests.py | 1 |
2 files changed, 15 insertions, 0 deletions
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py index 1b7bc0f9a1..c4cc62e82a 100644 --- a/python/pyspark/sql/readwriter.py +++ b/python/pyspark/sql/readwriter.py @@ -73,6 +73,13 @@ class DataFrameReader(object): self._jreader = self._jreader.schema(jschema) return self + @since(1.5) + def option(self, key, value): + """Adds an input option for the underlying data source. + """ + self._jreader = self._jreader.option(key, value) + return self + @since(1.4) def options(self, **options): """Adds input options for the underlying data source. @@ -235,6 +242,13 @@ class DataFrameWriter(object): self._jwrite = self._jwrite.format(source) return self + @since(1.5) + def option(self, key, value): + """Adds an output option for the underlying data source. + """ + self._jwrite = self._jwrite.option(key, value) + return self + @since(1.4) def options(self, **options): """Adds output options for the underlying data source. diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 5c2589089b..f90277697d 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -549,6 +549,7 @@ class SQLTests(ReusedPySparkTestCase): self.assertEqual(sorted(df.collect()), sorted(actual.collect())) df.write.mode("overwrite").options(noUse="this options will not be used in save.")\ + .option("noUse", "this option will not be used in save.")\ .format("json").save(path=tmpPath) actual =\ self.sqlCtx.read.format("json")\ |