From 8b4272814fb4585be120f183eb7c26bb8acde974 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Fri, 21 Oct 2022 11:29:26 +0200 Subject: Merging upstream version 9.0.1. Signed-off-by: Daniel Baumann --- tests/dataframe/integration/test_session.py | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 tests/dataframe/integration/test_session.py (limited to 'tests/dataframe/integration/test_session.py') diff --git a/tests/dataframe/integration/test_session.py b/tests/dataframe/integration/test_session.py new file mode 100644 index 0000000..ff1477b --- /dev/null +++ b/tests/dataframe/integration/test_session.py @@ -0,0 +1,28 @@ +from pyspark.sql import functions as F + +from sqlglot.dataframe.sql import functions as SF +from tests.dataframe.integration.dataframe_validator import DataFrameValidator + + +class TestSessionFunc(DataFrameValidator): + def test_sql_simple_select(self): + query = "SELECT fname, lname FROM employee" + df = self.spark.sql(query) + dfs = self.sqlglot.sql(query) + self.compare_spark_with_sqlglot(df, dfs) + + def test_sql_with_join(self): + query = """ + SELECT + e.employee_id + , s.store_id + FROM + employee e + INNER JOIN + store s + ON + e.store_id = s.store_id + """ + df = self.spark.sql(query).groupBy(F.col("store_id")).agg(F.countDistinct(F.col("employee_id"))) + dfs = self.sqlglot.sql(query).groupBy(SF.col("store_id")).agg(SF.countDistinct(SF.col("employee_id"))) + self.compare_spark_with_sqlglot(df, dfs, skip_schema_compare=True) -- cgit v1.2.3