Experiment with functional testing

.circleci/config.yml

@@ -8,16 +8,20 @@ jobs:
       - image: cimg/python:3.9.9
       - image: circleci/postgres:9.6.5-alpine-ram
 
+    environment:
+      POSTGRES_TEST_HOST: localhost
+      POSTGRES_TEST_USER: root
+      POSTGRES_TEST_PASS: ''
+      POSTGRES_TEST_PORT: 5432
+      POSTGRES_TEST_DBNAME: circle_test
+
     steps:
       - checkout
       - run:
-          name: "Run Tests - Postgres"
-          environment:
-            POSTGRES_TEST_HOST: localhost
-            POSTGRES_TEST_USER: root
-            POSTGRES_TEST_PASS: ''
-            POSTGRES_TEST_PORT: 5432
-            POSTGRES_TEST_DBNAME: circle_test
+          name: "Run Functional Tests - Postgres"
+          command: ./run_functional_test.sh postgres
+      - run:
+          name: "Run OG Tests - Postgres"
           command: ./run_test.sh postgres
       - store_artifacts:
           path: ./logs
@@ -28,7 +32,10 @@ jobs:
     steps:
       - checkout
       - run:
-          name: "Run Tests - Redshift"
+          name: "Run Functional Tests - Redshift"
+          command: ./run_functional_test.sh redshift
+      - run:
+          name: "Run OG Tests - Redshift"
           command: ./run_test.sh redshift
       - store_artifacts:
           path: ./logs
@@ -39,7 +46,10 @@ jobs:
     steps:
       - checkout
       - run:
-          name: "Run Tests - Snowflake"
+          name: "Run Functional Tests - Snowflake"
+          command: ./run_functional_test.sh snowflake
+      - run:
+          name: "Run OG Tests - Snowflake"
           command: ./run_test.sh snowflake
       - store_artifacts:
           path: ./logs          
@@ -55,7 +65,10 @@ jobs:
           name: "Set up credentials"
           command: echo $BIGQUERY_SERVICE_ACCOUNT_JSON > ${HOME}/bigquery-service-key.json
       - run:
-          name: "Run Tests - BigQuery"
+          name: "Run Functional Tests - BigQuery"
+          command: ./run_functional_test.sh bigquery
+      - run:
+          name: "Run OG Tests - BigQuery"
           command: ./run_test.sh bigquery
       - store_artifacts:
           path: ./logs

.gitignore

@@ -4,3 +4,6 @@ dbt_modules/
 dbt_packages/
 logs/
 venv/
+env/
+test.env
+__pycache__

dev-requirements.txt

@@ -0,0 +1,3 @@
+pytest
+pytest-dotenv
+dbt-tests-adapter

pytest.ini

@@ -0,0 +1,8 @@
+[pytest]
+filterwarnings =
+    ignore:.*'soft_unicode' has been renamed to 'soft_str'*:DeprecationWarning
+    ignore:unclosed file .*:ResourceWarning
+env_files =
+    test.env
+testpaths =
+    tests/functional

run_functional_test.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+VENV="venv/bin/activate"
+
+if [[ ! -f $VENV ]]; then
+    python3 -m venv venv
+    . $VENV
+
+    pip install --upgrade pip setuptools
+    pip install --pre "dbt-$1" -r dev-requirements.txt
+fi
+
+. $VENV
+python3 -m pytest tests/functional --profile $1

tests/conftest.py

@@ -0,0 +1,98 @@
+import pytest
+import os
+
+pytest_plugins = ["dbt.tests.fixtures.project"]
+
+
+def pytest_addoption(parser):
+    parser.addoption("--profile", action="store", default="apache_spark", type=str)
+
+
+# Using @pytest.mark.skip_adapter('apache_spark') uses the 'skip_by_adapter_type'
+# autouse fixture below
+def pytest_configure(config):
+    config.addinivalue_line(
+        "markers",
+        "skip_profile(profile): skip test for the given profile",
+    )
+    config.addinivalue_line(
+        "markers",
+        "only_profile(profile): only test the given profile",
+    )
+
+
+@pytest.fixture(scope="session")
+def dbt_profile_target(request):
+    profile_type = request.config.getoption("--profile")
+    if profile_type == "postgres":
+        target = postgres_target()
+    elif profile_type == "redshift":
+        target = redshift_target()
+    elif profile_type == "snowflake":
+        target = snowflake_target()
+    elif profile_type == "bigquery":
+        target = bigquery_target()
+    else:
+        raise ValueError(f"Invalid profile type '{profile_type}'")
+    return target
+
+
+def postgres_target():
+    return {
+        "type": "postgres",
+        "host": os.getenv('POSTGRES_TEST_HOST'),
+        "user": os.getenv('POSTGRES_TEST_USER'),
+        "pass": os.getenv('POSTGRES_TEST_PASS'),
+        "port": int(os.getenv('POSTGRES_TEST_PORT')),
+        "dbname": os.getenv('POSTGRES_TEST_DBNAME'),
+    }
+
+
+def redshift_target():
+    return {
+        "type": "redshift",
+        "host": os.getenv('REDSHIFT_TEST_HOST'),
+        "user": os.getenv('REDSHIFT_TEST_USER'),
+        "pass": os.getenv('REDSHIFT_TEST_PASS'),
+        "port": int(os.getenv('REDSHIFT_TEST_PORT')),
+        "dbname": os.getenv('REDSHIFT_TEST_DBNAME'),
+    }
+
+
+def bigquery_target():
+    return {
+        "type": "bigquery",
+        "method": "service-account",
+        "keyfile": os.getenv('BIGQUERY_SERVICE_KEY_PATH'),
+        "project": os.getenv('BIGQUERY_TEST_DATABASE'),
+    }
+
+
+def snowflake_target():
+    return {
+        "type": "snowflake",
+        "account": os.getenv('SNOWFLAKE_TEST_ACCOUNT'),
+        "user": os.getenv('SNOWFLAKE_TEST_USER'),
+        "password": os.getenv('SNOWFLAKE_TEST_PASSWORD'),
+        "role": os.getenv('SNOWFLAKE_TEST_ROLE'),
+        "database": os.getenv('SNOWFLAKE_TEST_DATABASE'),
+        "warehouse": os.getenv('SNOWFLAKE_TEST_WAREHOUSE'),
+    }
+
+
+@pytest.fixture(autouse=True)
+def skip_by_profile_type(request):
+    profile_type = request.config.getoption("--profile")
+    if request.node.get_closest_marker("skip_profile"):
+        for skip_profile_type in request.node.get_closest_marker("skip_profile").args:
+            if skip_profile_type == profile_type:
+                pytest.skip("skipped on '{profile_type}' profile")
+
+
+@pytest.fixture(autouse=True)
+def only_profile_type(request):
+    profile_type = request.config.getoption("--profile")
+    if request.node.get_closest_marker("only_profile"):
+        for only_profile_type in request.node.get_closest_marker("only_profile").args:
+            if only_profile_type != profile_type:
+                pytest.skip("skipped on '{profile_type}' profile")

tests/functional/cross_db_utils/base_cross_db_macro.py

@@ -0,0 +1,30 @@
+import os
+import pytest
+from dbt.tests.util import run_dbt
+from tests.functional.cross_db_utils.fixture_cross_db_macro import (
+    macros__test_assert_equal_sql,
+)
+
+
+class BaseCrossDbMacro:
+    # install this repo as a package!
+    @pytest.fixture(scope="class")
+    def packages(self):
+        return {"packages": [{"local": os.getcwd()}]}
+
+    # setup
+    @pytest.fixture(scope="class")
+    def macros(self):
+        return {"test_assert_equal.sql": macros__test_assert_equal_sql}
+
+    # each child class will reimplement 'models' + 'seeds'
+    def seeds(self):
+        return {}
+
+    def models(self):
+        return {}
+
+    # actual test sequence
+    def test_build_assert_equal(self, project):
+        run_dbt(['deps'])
+        run_dbt(['build'])    # seed, model, test -- all handled by dbt

tests/functional/cross_db_utils/fixture_any_value.py

@@ -0,0 +1,61 @@
+
+# any_value
+
+seeds__data_any_value_csv = """id,key_name,static_col
+1,abc,dbt
+2,abc,dbt
+3,jkl,dbt
+4,jkl,dbt
+5,jkl,dbt
+6,xyz,test
+"""
+
+
+seeds__data_any_value_expected_csv = """key_name,static_col,num_rows
+abc,dbt,2
+jkl,dbt,3
+xyz,test,1
+"""
+
+
+models__test_any_value_sql = """
+with data as (
+
+    select * from {{ ref('data_any_value') }}
+
+),
+
+data_output as (
+
+    select * from {{ ref('data_any_value_expected') }}
+
+),
+
+calculate as (
+    select
+        key_name,
+        {{ dbt_utils.any_value('static_col') }} as static_col,
+        count(id) as num_rows
+    from data
+    group by key_name
+)
+
+select
+    calculate.num_rows as actual,
+    data_output.num_rows as expected
+from calculate
+left join data_output
+on calculate.key_name = data_output.key_name
+and calculate.static_col = data_output.static_col
+"""
+
+
+models__test_any_value_yml = """
+version: 2
+models:
+  - name: test_any_value
+    tests:
+      - assert_equal:
+          actual: actual
+          expected: expected
+"""

tests/functional/cross_db_utils/fixture_bool_or.py

@@ -0,0 +1,63 @@
+
+# bool_or
+
+seeds__data_bool_or_csv = """key,val1,val2
+abc,1,1
+abc,1,0
+def,1,0
+hij,1,1
+hij,1,
+klm,1,0
+klm,1,
+"""
+
+
+seeds__data_bool_or_expected_csv = """key,value
+abc,true
+def,false
+hij,true
+klm,false
+"""
+
+
+models__test_bool_or_sql = """
+with data as (
+
+    select * from {{ ref('data_bool_or') }}
+
+),
+
+data_output as (
+
+    select * from {{ ref('data_bool_or_expected') }}
+
+),
+
+calculate as (
+
+    select
+        key,
+        {{ dbt_utils.bool_or('val1 = val2') }} as value
+    from data
+    group by key
+
+)
+
+select
+    calculate.value as actual,
+    data_output.value as expected
+from calculate
+left join data_output
+on calculate.key = data_output.key
+"""
+
+
+models__test_bool_or_yml = """
+version: 2
+models:
+  - name: test_bool_or
+    tests:
+      - assert_equal:
+          actual: actual
+          expected: expected
+"""

tests/functional/cross_db_utils/fixture_cast_bool_to_text.py

@@ -0,0 +1,30 @@
+
+# cast_bool_to_text
+
+models__test_cast_bool_to_text_sql = """
+with data as (
+
+    select 0=1 as input, 'false' as expected union all
+    select 1=1 as input, 'true' as expected union all
+    select null as input, null as expected
+
+)
+
+select
+
+    {{ dbt_utils.cast_bool_to_text("input") }} as actual,
+    expected
+
+from data
+"""
+
+
+models__test_cast_bool_to_text_yml = """
+version: 2
+models:
+  - name: test_cast_bool_to_text
+    tests:
+      - assert_equal:
+          actual: actual
+          expected: expected
+"""