def create_table_using_datasource(self, provider, schemaddl=False):
sparkSession = SnappySession(self.sc)
df = sparkSession._sc.parallelize(SnappyContextTests.testdata, 5).toDF(["COL1", "COL2", "COL3"])
if schemaddl is False:
sparkSession.createTable(SnappyContextTests.tablename, provider, df.schema)
else:
sparkSession.createTable(SnappyContextTests.tablename, provider, "(COL1 INT , COL2 INT , COL3 INT)")
df.write.format("row").mode("append").saveAsTable(SnappyContextTests.tablename)
def test_create_table_without_schema(self):
self.drop_table(True)
snappy = SnappySession(self.sc)
#should use default provider which is parquet and schema will be picked from parquet file
parquetPath = os.path.join(os.path.dirname(os.path.abspath(__file__)), "../../test_support/kv.parquet")
snappy.createTable(SnappyContextTests.tablename, path = parquetPath)
self.verify_table_rows(3)
self.drop_table()
def create_table_using_datasource(self, provider, schemaddl=False):
sparkSession = SnappySession(self.sc)
schema = StructType().add("col1", IntegerType()).add("col2", IntegerType()).add("col3", IntegerType())
input = SnappyContextTests.testdata
df = sparkSession.createDataFrame(input, schema)
if schemaddl is False:
sparkSession.createTable(SnappyContextTests.tablename, provider, schema)
else:
sparkSession.createTable(SnappyContextTests.tablename, provider, "(COL1 INT , COL2 INT , COL3 INT)")
df.write.format("row").mode("append").saveAsTable(SnappyContextTests.tablename)
def create_table_using_datasource(self, provider, schemaddl=False):
sparkSession = SnappySession(self.sc)
df = sparkSession._sc.parallelize(SnappyContextTests.testdata,
5).toDF(["COL1", "COL2", "COL3"])
if schemaddl is False:
sparkSession.createTable(SnappyContextTests.tablename, provider,
df.schema)
else:
sparkSession.createTable(SnappyContextTests.tablename, provider,
"(COL1 INT , COL2 INT , COL3 INT)")
df.write.format("row").mode("append").saveAsTable(
SnappyContextTests.tablename)
