[SPARK-15171][SQL] Deprecate registerTempTable and add dataset.createTempView

## What changes were proposed in this pull request?

Deprecates registerTempTable and add dataset.createTempView, dataset.createOrReplaceTempView.

## How was this patch tested?

Unit tests.

Author: Sean Zhong <seanzhong@databricks.com>

Closes #12945 from clockfly/spark-15171.

4 files changed, 59 insertions, 28 deletions

diff --git a/python/pyspark/sql/catalog.py b/python/pyspark/sql/catalog.py
index 9cfdd0a99f..812dbba59e 100644
--- a/python/pyspark/sql/catalog.py
+++ b/python/pyspark/sql/catalog.py
@@ -166,34 +166,20 @@ class Catalog(object):
         return DataFrame(df, self._sparkSession._wrapped)
 
     @since(2.0)
-    def dropTempTable(self, tableName):
-        """Drops the temporary table with the given table name in the catalog.
-        If the table has been cached before, then it will also be uncached.
+    def dropTempView(self, viewName):
+        """Drops the temporary view with the given view name in the catalog.
+        If the view has been cached before, then it will also be uncached.
 
-        >>> spark.createDataFrame([(1, 1)]).registerTempTable("my_table")
+        >>> spark.createDataFrame([(1, 1)]).createTempView("my_table")
         >>> spark.table("my_table").collect()
         [Row(_1=1, _2=1)]
-        >>> spark.catalog.dropTempTable("my_table")
+        >>> spark.catalog.dropTempView("my_table")
         >>> spark.table("my_table") # doctest: +IGNORE_EXCEPTION_DETAIL
         Traceback (most recent call last):
             ...
         AnalysisException: ...
         """
-        self._jcatalog.dropTempTable(tableName)
-
-    @since(2.0)
-    def registerTable(self, df, tableName):
-        """Registers the given :class:`DataFrame` as a temporary table in the catalog.
-
-        >>> df = spark.createDataFrame([(2, 1), (3, 1)])
-        >>> spark.catalog.registerTable(df, "my_cool_table")
-        >>> spark.table("my_cool_table").collect()
-        [Row(_1=2, _2=1), Row(_1=3, _2=1)]
-        """
-        if isinstance(df, DataFrame):
-            self._jsparkSession.registerTable(df._jdf, tableName)
-        else:
-            raise ValueError("Can only register DataFrame as table")
+        self._jcatalog.dropTempView(viewName)
 
     @ignore_unicode_prefix
     @since(2.0)
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py
index 02e742c124..ca111ae9bb 100644
--- a/python/pyspark/sql/context.py
+++ b/python/pyspark/sql/context.py
@@ -302,7 +302,7 @@ class SQLContext(object):
 
         >>> sqlContext.registerDataFrameAsTable(df, "table1")
         """
-        self.sparkSession.catalog.registerTable(df, tableName)
+        df.createOrReplaceTempView(tableName)
 
     @since(1.6)
     def dropTempTable(self, tableName):
@@ -311,7 +311,7 @@ class SQLContext(object):
         >>> sqlContext.registerDataFrameAsTable(df, "table1")
         >>> sqlContext.dropTempTable("table1")
         """
-        self.sparkSession.catalog.dropTempTable(tableName)
+        self.sparkSession.catalog.dropTempView(tableName)
 
     @since(1.3)
     def createExternalTable(self, tableName, path=None, source=None, schema=None, **options):
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 49b4818bcc..a0264ce1ac 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -119,11 +119,55 @@ class DataFrame(object):
         that was used to create this :class:`DataFrame`.
 
         >>> df.registerTempTable("people")
-        >>> df2 = sqlContext.sql("select * from people")
+        >>> df2 = spark.sql("select * from people")
         >>> sorted(df.collect()) == sorted(df2.collect())
         True
+        >>> spark.catalog.dropTempView("people")
+
+        .. note:: Deprecated in 2.0, use createOrReplaceTempView instead.
+        """
+        self._jdf.createOrReplaceTempView(name)
+
+    @since(2.0)
+    def createTempView(self, name):
+        """Creates a temporary view with this DataFrame.
+
+        The lifetime of this temporary table is tied to the :class:`SparkSession`
+        that was used to create this :class:`DataFrame`.
+        throws :class:`TempTableAlreadyExistsException`, if the view name already exists in the
+        catalog.
+
+        >>> df.createTempView("people")
+        >>> df2 = spark.sql("select * from people")
+        >>> sorted(df.collect()) == sorted(df2.collect())
+        True
+        >>> df.createTempView("people")  # doctest: +IGNORE_EXCEPTION_DETAIL
+        Traceback (most recent call last):
+        ...
+        Py4JJavaError: ...
+        : org.apache.spark.sql.catalyst.analysis.TempTableAlreadyExistsException...
+        >>> spark.catalog.dropTempView("people")
+
+        """
+        self._jdf.createTempView(name)
+
+    @since(2.0)
+    def createOrReplaceTempView(self, name):
+        """Creates or replaces a temporary view with this DataFrame.
+
+        The lifetime of this temporary table is tied to the :class:`SparkSession`
+        that was used to create this :class:`DataFrame`.
+
+        >>> df.createOrReplaceTempView("people")
+        >>> df2 = df.filter(df.age > 3)
+        >>> df2.createOrReplaceTempView("people")
+        >>> df3 = spark.sql("select * from people")
+        >>> sorted(df3.collect()) == sorted(df2.collect())
+        True
+        >>> spark.catalog.dropTempView("people")
+
         """
-        self._jdf.registerTempTable(name)
+        self._jdf.createOrReplaceTempView(name)
 
     @property
     @since(1.4)
@@ -1479,12 +1523,13 @@ class DataFrameStatFunctions(object):
 def _test():
     import doctest
     from pyspark.context import SparkContext
-    from pyspark.sql import Row, SQLContext
+    from pyspark.sql import Row, SQLContext, SparkSession
     import pyspark.sql.dataframe
     globs = pyspark.sql.dataframe.__dict__.copy()
     sc = SparkContext('local[4]', 'PythonTest')
     globs['sc'] = sc
     globs['sqlContext'] = SQLContext(sc)
+    globs['spark'] = SparkSession(sc)
     globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')])\
         .toDF(StructType([StructField('age', IntegerType()),
                           StructField('name', StringType())]))
diff --git a/python/pyspark/sql/session.py b/python/pyspark/sql/session.py
index 4ee9ab8ab2..ae314359d5 100644
--- a/python/pyspark/sql/session.py
+++ b/python/pyspark/sql/session.py
@@ -160,7 +160,7 @@ class SparkSession(object):
         ...     b=True, list=[1, 2, 3], dict={"s": 0}, row=Row(a=1),
         ...     time=datetime(2014, 8, 1, 14, 1, 5))])
         >>> df = allTypes.toDF()
-        >>> df.registerTempTable("allTypes")
+        >>> df.createOrReplaceTempView("allTypes")
         >>> spark.sql('select i+1, d+1, not b, list[1], dict["s"], time, row.a '
         ...            'from allTypes where b and i > 0').collect()
         [Row((i + CAST(1 AS BIGINT))=2, (d + CAST(1 AS DOUBLE))=2.0, (NOT b)=False, list[1]=2, \
@@ -484,7 +484,7 @@ class SparkSession(object):
 
         :return: :class:`DataFrame`
 
-        >>> spark.catalog.registerTable(df, "table1")
+        >>> df.createOrReplaceTempView("table1")
         >>> df2 = spark.sql("SELECT field1 AS f1, field2 as f2 from table1")
         >>> df2.collect()
         [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
@@ -497,7 +497,7 @@ class SparkSession(object):
 
         :return: :class:`DataFrame`
 
-        >>> spark.catalog.registerTable(df, "table1")
+        >>> df.createOrReplaceTempView("table1")
         >>> df2 = spark.table("table1")
         >>> sorted(df.collect()) == sorted(df2.collect())
         True