Add testing for date_format and update doc

hi-primus · Sep 21, 2017 · 0ba18da · 0ba18da
1 parent 78d4ef6
commit 0ba18da
Show file tree

Hide file tree

Showing 2 changed files with 43 additions and 2 deletions.
diff --git a/docs/index.rst b/docs/index.rst
@@ -1585,12 +1585,12 @@ date_transform(self, column, current_format, output_format)
             StructField("dates", StringType(), True),
             StructField("population", IntegerType(), True)])
 
-    countries = ['1991/02/25', '1998/05/10', '1993/03/15', '1992/07/17']
+    dates = ['1991/02/25', '1998/05/10', '1993/03/15', '1992/07/17']
     cities = ['Caracas', 'Ccs', '   São Paulo   ', '~Madrid']
     population = [37800000,19795791,12341418,6489162]
 
     # Dataframe:
-    df = op.spark.createDataFrame(list(zip(cities, countries, population)), schema=schema)
+    df = op.spark.createDataFrame(list(zip(cities, dates, population)), schema=schema)
 
     df.show()
 

diff --git a/tests/tests.py b/tests/tests.py
@@ -34,6 +34,27 @@ def create_df(spark_session):
         sys.exit(1)
 
 
+def create_other_df(spark_session):
+    try:
+        # Building a simple dataframe:
+        schema = StructType([
+            StructField("city", StringType(), True),
+            StructField("dates", StringType(), True),
+            StructField("population", IntegerType(), True)])
+
+        dates = ['1991/02/25', '1998/05/10', '1993/03/15', '1992/07/17']
+        cities = ['Caracas', 'Ccs', '   São Paulo   ', '~Madrid']
+        population = [37800000, 19795791, 12341418, 6489162]
+
+        # Dataframe:
+        df = spark_session.createDataFrame(list(zip(cities, dates, population)), schema=schema)
+        assert_spark_df(df)
+        return df
+    except RuntimeError:
+        logger.exception('Could not create other dataframe.')
+        sys.exit(1)
+
+
 def test_transformer(spark_session):
     try:
         transformer = op.DataFrameTransformer(create_df(spark_session))
@@ -156,3 +177,23 @@ def test_lookup(spark_session):
         sys.exit(1)
 
 
+def test_move_col(spark_session):
+    try:
+        transformer = op.DataFrameTransformer(create_df(spark_session))
+        transformer.move_col('city', 'country', position='after')
+        assert_spark_df(transformer.get_data_frame)
+    except RuntimeError:
+        logger.exception('Could not run move_col().')
+        sys.exit(1)
+
+
+def test_date_transform(spark_session):
+    try:
+        transformer = op.DataFrameTransformer(create_other_df(spark_session))
+        transformer.date_transform(columns="dates",
+                                   current_format="yyyy/mm/dd",
+                                   output_format="dd-mm-yyyy")
+        assert_spark_df(transformer.get_data_frame)
+    except RuntimeError:
+        logger.exception('Could not run date_transform().')
+        sys.exit(1)