Add column rename example

CHANGELOG.md

@@ -1,3 +1,5 @@
+- Add example with column rename macro ([PR](https://github.com/godatadriven/pytest-dbt-core/pull/19))
+
 ## [0.1.0] - 2022-07-22
 
 - Run test examples from docs ([issue](https://github.com/godatadriven/pytest-dbt-core/issues/14), [PR](https://github.com/godatadriven/pytest-dbt-core/pull/17))

docs/source/_static/dbt_project/macros/normalize_column_names.sql

@@ -0,0 +1,18 @@
+{% macro normalize_column_names(column_names) %}
+{%- set re = modules.re -%}
+
+{%- for column_name in column_names -%}
+
+     {%- set normalized_column_name = re.sub('[!?@#$()%&]', '', column_name).strip().replace(' ', '_').replace('.', '_').rstrip('_').lower() -%}
+
+     {# Columns should not start with digits #}
+     {%- if normalized_column_name[0].isdigit()  -%}
+          {% set normalized_column_name = '_' + normalized_column_name-%}
+     {% endif -%}
+
+     `{{ column_name }}` as {{ normalized_column_name }}
+     {%- if not loop.last -%}, {% endif -%}
+
+{%- endfor -%}
+
+{% endmacro %}

docs/source/_static/dbt_project/packages.yml

@@ -1,3 +1,5 @@
 packages:
 - package: dbt-labs/spark_utils
   version: 0.3.0
+- package: dbt-labs/dbt_utils
+  version: 0.8.6

docs/source/_static/dbt_project/tests/test_normalize_column_names.py

@@ -0,0 +1,34 @@
+import pytest
+from dbt.clients.jinja import MacroGenerator
+from pyspark.sql import SparkSession
+
+
+@pytest.mark.parametrize(
+    "macro_generator",
+    ["macro.dbt_project.normalize_column_names"],
+    indirect=True,
+)
+@pytest.mark.parametrize(
+    "column_name,expected_column_name",
+    [
+        ("unit", "unit"),
+        ("column with spaces", "column_with_spaces"),
+        ("c!h?a#r$a(c)t%e&rs", "characters"),
+        ("trailing white spaces  ", "trailing_white_spaces"),
+        ("column.with.periods", "column_with_periods"),
+        ("9leading number", "_9leading_number"),
+        ("UPPERCASE", "uppercase"),
+    ],
+)
+def test_normalize_column_names(
+    spark_session: SparkSession,
+    macro_generator: MacroGenerator,
+    column_name: str,
+    expected_column_name: str,
+) -> None:
+    """Test normalize column names with different scenarios."""
+    normalized_column_names = macro_generator([column_name])
+    out = spark_session.sql(
+        f"SELECT {normalized_column_names} FROM (SELECT True AS `{column_name}`)"
+    )
+    assert out.columns[0] == expected_column_name, normalized_column_names

docs/source/dbt_spark.rst

@@ -33,25 +33,8 @@ Usage
 
 Use the `spark_session` fixture to set-up the unit test for your macro:
 
-.. code-block:: python
-
-   from __future__ import annotations
-
-   import pytest
-   from dbt.clients.jinja import MacroGenerator
-   from pyspark.sql import SparkSession
-
-
-   @pytest.mark.parametrize(
-       "macro_generator", ["macro.spark_utils.get_tables"], indirect=True
-   )
-   def test_create_table(
-       spark_session: SparkSession, macro_generator: MacroGenerator
-   ) -> None:
-       expected_table = "default.example"
-       spark_session.sql(f"CREATE TABLE {expected_table} (id int) USING parquet")
-       tables = macro_generator()
-       assert tables == [expected_table]
+.. literalinclude :: _static/dbt_project/tests/test_spark_get_tables.py
+   :language: python
 
 Test
 ****

docs/source/index.rst

@@ -22,9 +22,14 @@ Install `pytest-dbt-core` via pip with
 Usage
 ******
 
+Create a macro:
+
+.. literalinclude :: _static/dbt_project/macros/normalize_column_names.sql
+   :language: jinja
+
 Unit test a macro:
 
-.. literalinclude :: _static/dbt_project/tests/test_spark_get_tables.py
+.. literalinclude :: _static/dbt_project/tests/test_normalize_column_names.py
    :language: python
 
 .. toctree::