Refactor to make dbt snowflake override in a test easier.

* Flexibilize MarkupSafe pinned version

The current `MarkupSafe` pinned version has been added in #4746 as a
temporary fix for #4745.

However, the current restrictive approach isn't compatible with other
libraries that could require an even older version of `MarkupSafe`, like
Airflow `2.2.2` [0], which requires `markupsafe>=1.1.1, <2.0`.

To avoid that issue, we can allow a greater range of supported
`MarkupSafe` versions. Considering the direct dependency `dbt-core` has
is `Jinja2==2.11.3`, we can use its pinning as the lower bound, which is
`MarkupSafe>=0.23` [1].

This fix should be also backported this to `1.0.latest` for inclusion in
the next v1.0 patch.

[0] https://github.com/adamantike/airflow/blob/2.2.2/setup.cfg#L125
[1] https://github.com/pallets/jinja/blob/2.11.3/setup.py#L53

.changes/unreleased/Under the Hood-20220409-040539.yaml

@@ -0,0 +1,7 @@
+kind: Under the Hood
+body: Migrating 005_simple_seed to the new test framework.
+time: 2022-04-09T04:05:39.20045-07:00
+custom:
+  Author: versusfacit
+  Issue: "200"
+  PR: "5013"

test/integration/005_simple_seed_tests/macros/schema_test.sql

@@ -1,22 +0,0 @@
-
-{% test column_type(model, column_name, type) %}
-
-    {% set cols = adapter.get_columns_in_relation(model) %}
-
-    {% set col_types = {} %}
-    {% for col in cols %}
-        {% do col_types.update({col.name: col.data_type}) %}
-    {% endfor %}
-
-    {% set validation_message = 'Got a column type of ' ~ col_types.get(column_name) ~ ', expected ' ~ type %}
-
-    {% set val = 0 if col_types.get(column_name) == type else 1 %}
-    {% if val == 1 and execute %}
-        {{ log(validation_message, info=True) }}
-    {% endif %}
-
-    select '{{ validation_message }}' as validation_error
-    from (select true) as nothing
-    where {{ val }} = 1
-
-{% endtest %}

test/integration/005_simple_seed_tests/models-downstream-seed/model.sql

@@ -1 +0,0 @@
-select * from {{ ref('seed_actual') }}

test/integration/005_simple_seed_tests/models-exist/model.sql

@@ -1 +0,0 @@
-select * from {{ this.schema }}.seed_expected

test/integration/005_simple_seed_tests/models-pg/schema.yml

@@ -1,47 +0,0 @@
-version: 2
-seeds:
-- name: seed_enabled
-  columns:
-  - name: birthday
-    tests:
-    - column_type:
-        type: date
-  - name: id
-    tests:
-    - column_type:
-        type: text
-
-- name: seed_tricky
-  columns:
-  - name: id
-    tests:
-    - column_type:
-        type: integer
-  - name: id_str
-    tests:
-    - column_type:
-        type: text
-  - name: a_bool
-    tests:
-    - column_type:
-        type: boolean
-  - name: looks_like_a_bool
-    tests:
-    - column_type:
-        type: text
-  - name: a_date
-    tests:
-    - column_type:
-        type: timestamp without time zone
-  - name: looks_like_a_date
-    tests:
-    - column_type:
-        type: text
-  - name: relative
-    tests:
-    - column_type:
-        type: text
-  - name: weekday
-    tests:
-    - column_type:
-        type: text

test/integration/005_simple_seed_tests/seeds-bad/seed.csv

@@ -1,3 +0,0 @@
-a,b,c
-1,7,23,90,5
-2

test/integration/005_simple_seed_tests/seeds-big/.gitignore

@@ -1 +0,0 @@
-*.csv

test/integration/005_simple_seed_tests/seeds-config/seed_disabled.csv

@@ -1,21 +0,0 @@
-id,first_name,email,ip_address,birthday
-1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
-2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
-3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57
-4,Sandra,sgeorge3@livejournal.com,229.235.252.98,1973-07-19 10:52:43
-5,Fred,fwoods4@google.cn,78.229.170.124,2012-09-30 16:38:29
-6,Stephen,shanson5@livejournal.com,182.227.157.105,1995-11-07 21:40:50
-7,William,wmartinez6@upenn.edu,135.139.249.50,1982-09-05 03:11:59
-8,Jessica,jlong7@hao123.com,203.62.178.210,1991-10-16 11:03:15
-9,Douglas,dwhite8@tamu.edu,178.187.247.1,1979-10-01 09:49:48
-10,Lisa,lcoleman9@nydailynews.com,168.234.128.249,2011-05-26 07:45:49
-11,Ralph,rfieldsa@home.pl,55.152.163.149,1972-11-18 19:06:11
-12,Louise,lnicholsb@samsung.com,141.116.153.154,2014-11-25 20:56:14
-13,Clarence,cduncanc@sfgate.com,81.171.31.133,2011-11-17 07:02:36
-14,Daniel,dfranklind@omniture.com,8.204.211.37,1980-09-13 00:09:04
-15,Katherine,klanee@auda.org.au,176.96.134.59,1997-08-22 19:36:56
-16,Billy,bwardf@wikia.com,214.108.78.85,2003-10-19 02:14:47
-17,Annie,agarzag@ocn.ne.jp,190.108.42.70,1988-10-28 15:12:35
-18,Shirley,scolemanh@fastcompany.com,109.251.164.84,1988-08-24 10:50:57
-19,Roger,rfrazieri@scribd.com,38.145.218.108,1985-12-31 15:17:15
-20,Lillian,lstanleyj@goodreads.com,47.57.236.17,1970-06-08 02:09:05

test/integration/005_simple_seed_tests/seeds-config/seed_enabled.csv

@@ -1,21 +0,0 @@
-id,first_name,email,ip_address,birthday
-1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
-2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
-3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57
-4,Sandra,sgeorge3@livejournal.com,229.235.252.98,1973-07-19 10:52:43
-5,Fred,fwoods4@google.cn,78.229.170.124,2012-09-30 16:38:29
-6,Stephen,shanson5@livejournal.com,182.227.157.105,1995-11-07 21:40:50
-7,William,wmartinez6@upenn.edu,135.139.249.50,1982-09-05 03:11:59
-8,Jessica,jlong7@hao123.com,203.62.178.210,1991-10-16 11:03:15
-9,Douglas,dwhite8@tamu.edu,178.187.247.1,1979-10-01 09:49:48
-10,Lisa,lcoleman9@nydailynews.com,168.234.128.249,2011-05-26 07:45:49
-11,Ralph,rfieldsa@home.pl,55.152.163.149,1972-11-18 19:06:11
-12,Louise,lnicholsb@samsung.com,141.116.153.154,2014-11-25 20:56:14
-13,Clarence,cduncanc@sfgate.com,81.171.31.133,2011-11-17 07:02:36
-14,Daniel,dfranklind@omniture.com,8.204.211.37,1980-09-13 00:09:04
-15,Katherine,klanee@auda.org.au,176.96.134.59,1997-08-22 19:36:56
-16,Billy,bwardf@wikia.com,214.108.78.85,2003-10-19 02:14:47
-17,Annie,agarzag@ocn.ne.jp,190.108.42.70,1988-10-28 15:12:35
-18,Shirley,scolemanh@fastcompany.com,109.251.164.84,1988-08-24 10:50:57
-19,Roger,rfrazieri@scribd.com,38.145.218.108,1985-12-31 15:17:15
-20,Lillian,lstanleyj@goodreads.com,47.57.236.17,1970-06-08 02:09:05

test/integration/005_simple_seed_tests/seeds-config/seed_tricky.csv

@@ -1,7 +0,0 @@
-id,id_str,a_bool,looks_like_a_bool,a_date,looks_like_a_date,relative,weekday
-1,1,true,true,2019-01-01 12:32:30,2019-01-01 12:32:30,tomorrow,Saturday
-2,2,True,True,2019-01-01 12:32:31,2019-01-01 12:32:31,today,Sunday
-3,3,TRUE,TRUE,2019-01-01 12:32:32,2019-01-01 12:32:32,yesterday,Monday
-4,4,false,false,2019-01-01 01:32:32,2019-01-01 01:32:32,tomorrow,Saturday
-5,5,False,False,2019-01-01 01:32:32,2019-01-01 01:32:32,today,Sunday
-6,6,FALSE,FALSE,2019-01-01 01:32:32,2019-01-01 01:32:32,yesterday,Monday

test/integration/005_simple_seed_tests/seeds-dottedseed/seed.with.dots.csv

@@ -1,2 +0,0 @@
-id
-1

test/integration/005_simple_seed_tests/test_seed_type_override.py

@@ -1,61 +0,0 @@
-from test.integration.base import DBTIntegrationTest, use_profile
-
-
-class TestSimpleSeedColumnOverride(DBTIntegrationTest):
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-config'],
-            'macro-paths': ['macros'],
-            'seeds': {
-                'test': {
-                    'enabled': False,
-                    'quote_columns': True,
-                    'seed_enabled': {
-                        'enabled': True,
-                        '+column_types': self.seed_enabled_types()
-                    },
-                    'seed_tricky': {
-                        'enabled': True,
-                        '+column_types': self.seed_tricky_types(),
-                    },
-                },
-            },
-        }
-
-
-class TestSimpleSeedColumnOverridePostgres(TestSimpleSeedColumnOverride):
-    @property
-    def models(self):
-        return "models-pg"
-
-    @property
-    def profile_config(self):
-        return self.postgres_profile()
-
-    def seed_enabled_types(self):
-        return {
-            "id": "text",
-            "birthday": "date",
-        }
-
-    def seed_tricky_types(self):
-        return {
-            'id_str': 'text',
-            'looks_like_a_bool': 'text',
-            'looks_like_a_date': 'text',
-        }
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_with_column_override_postgres(self):
-        results = self.run_dbt(["seed", "--show"])
-        self.assertEqual(len(results),  2)
-        results = self.run_dbt(["test"])
-        self.assertEqual(len(results),  10)
-

test/integration/005_simple_seed_tests/test_simple_seed.py

@@ -1,349 +0,0 @@
-import os
-import csv
-from test.integration.base import DBTIntegrationTest, use_profile
-
-
-class TestSimpleSeed(DBTIntegrationTest):
-
-    def setUp(self):
-        DBTIntegrationTest.setUp(self)
-        self.run_sql_file("seed.sql")
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models-downstream-seed"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds'],
-            'seeds': {
-                'quote_columns': False,
-            }
-        }
-
-    def use_full_refresh_project(self, full_refresh: bool):
-        overrides = {
-            'seeds': {
-                'quote_columns': False,
-                'full_refresh': full_refresh,
-            }
-        }
-        self.use_default_project(overrides)
-
-    def _seed_and_run(self):
-        assert len(self.run_dbt(['seed'])) == 1
-        self.assertTablesEqual('seed_actual', 'seed_expected')
-
-        assert len(self.run_dbt(['run'])) == 1
-        self.assertTablesEqual('model', 'seed_expected')
-
-    def _after_seed_model_state(self, cmd, exists: bool):
-        assert len(self.run_dbt(cmd)) == 1
-        self.assertTablesEqual('seed_actual', 'seed_expected')
-        if exists:
-            self.assertTableDoesExist('model')
-        else:
-            self.assertTableDoesNotExist('model')
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed(self):
-        self._seed_and_run()
-
-        # this should truncate the seed_actual table, then re-insert.
-        self._after_seed_model_state(['seed'], exists=True)
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_full_refresh_flag(self):
-        self._seed_and_run()
-
-        # this should drop the seed_actual table, then re-create it, so the
-        # model won't exist.
-        self._after_seed_model_state(['seed', '--full-refresh'], exists=False)
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_full_refresh_config(self):
-        self._seed_and_run()
-
-        # set the full_refresh config to False
-        self.use_full_refresh_project(False)
-
-        self._after_seed_model_state(['seed'], exists=True)
-        # make sure we ignore the full-refresh flag (the config is higher
-        # priority than the flag)
-        self._after_seed_model_state(['seed', '--full-refresh'], exists=True)
-
-        # this should drop the seed_actual table, then re-create it, so the
-        # model won't exist.
-        self.use_full_refresh_project(True)
-        self._after_seed_model_state(['seed'], exists=False)
-
-
-class TestSimpleSeedCustomSchema(DBTIntegrationTest):
-
-    def setUp(self):
-        super().setUp()
-        self.run_sql_file("seed.sql")
-        self._created_schemas.add(
-            self._get_schema_fqn(self.default_database, self.custom_schema_name())
-        )
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds'],
-            'seeds': {
-                "schema": "custom_schema",
-                'quote_columns': False,
-            },
-        }
-
-    def custom_schema_name(self):
-        return "{}_{}".format(self.unique_schema(), 'custom_schema')
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_with_schema(self):
-        schema_name = self.custom_schema_name()
-
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-        self.assertTablesEqual("seed_actual","seed_expected", table_a_schema=schema_name)
-
-        # this should truncate the seed_actual table, then re-insert
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-        self.assertTablesEqual("seed_actual","seed_expected", table_a_schema=schema_name)
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_with_drop_and_schema(self):
-        schema_name = "{}_{}".format(self.unique_schema(), 'custom_schema')
-
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-        self.assertTablesEqual("seed_actual","seed_expected", table_a_schema=schema_name)
-
-        # this should drop the seed table, then re-create
-        results = self.run_dbt(["seed", "--full-refresh"])
-        self.assertEqual(len(results),  1)
-        self.assertTablesEqual("seed_actual","seed_expected", table_a_schema=schema_name)
-
-
-class TestSimpleSeedDisabled(DBTIntegrationTest):
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-config'],
-            'seeds': {
-                "test": {
-                    "seed_enabled": {
-                        "enabled": True
-                    },
-                    "seed_disabled": {
-                        "enabled": False
-                    }
-                },
-                'quote_columns': False,
-            },
-        }
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_with_disabled(self):
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  2)
-        self.assertTableDoesExist('seed_enabled')
-        self.assertTableDoesNotExist('seed_disabled')
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_selection(self):
-        results = self.run_dbt(['seed', '--select', 'seed_enabled'])
-        self.assertEqual(len(results),  1)
-        self.assertTableDoesExist('seed_enabled')
-        self.assertTableDoesNotExist('seed_disabled')
-        self.assertTableDoesNotExist('seed_tricky')
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed_exclude(self):
-        results = self.run_dbt(['seed', '--exclude', 'seed_enabled'])
-        self.assertEqual(len(results),  1)
-        self.assertTableDoesNotExist('seed_enabled')
-        self.assertTableDoesNotExist('seed_disabled')
-        self.assertTableDoesExist('seed_tricky')
-
-
-class TestSeedParsing(DBTIntegrationTest):
-    def setUp(self):
-        super().setUp()
-        self.run_sql_file("seed.sql")
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models-exist"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-bad'],
-            'seeds': {
-                'quote_columns': False,
-            },
-        }
-
-    @use_profile('postgres')
-    def test_postgres_dbt_run_skips_seeds(self):
-        # run does not try to parse the seed files
-        self.assertEqual(len(self.run_dbt(['run'])), 1)
-
-        # make sure 'dbt seed' fails, otherwise our test is invalid!
-        self.run_dbt(['seed'], expect_pass=False)
-
-
-class TestSimpleSeedWithBOM(DBTIntegrationTest):
-
-    def setUp(self):
-        DBTIntegrationTest.setUp(self)
-        self.run_sql_file("seed.sql")
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-bom'],
-            'seeds': {
-                'quote_columns': False,
-            },
-        }
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed(self):
-        # first make sure nobody "fixed" the file by accident
-        seed_path = os.path.join(self.config.seed_paths[0], 'seed_bom.csv')
-        # 'data-bom/seed_bom.csv'
-        with open(seed_path, encoding='utf-8') as fp:
-            self.assertEqual(fp.read(1), u'\ufeff')
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-        self.assertTablesEqual("seed_bom", "seed_expected")
-
-
-class TestSimpleSeedWithUnicode(DBTIntegrationTest):
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-unicode'],
-            'seeds': {
-                'quote_columns': False,
-            }
-        }
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed(self):
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-
-
-class TestSimpleSeedWithDots(DBTIntegrationTest):
-
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-dottedseed'],
-            'seeds': {
-                'quote_columns': False,
-            }
-        }
-
-    @use_profile('postgres')
-    def test_postgres_simple_seed(self):
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-        
-class TestSimpleBigSeedBatched(DBTIntegrationTest):
-    @property
-    def schema(self):
-        return "simple_seed_005"
-
-    @property
-    def models(self):
-        return "models"
-
-    @property
-    def project_config(self):
-        return {
-            'config-version': 2,
-            'seed-paths': ['seeds-big'],
-            'seeds': {
-                'quote_columns': False,
-            }
-        }
-
-    def test_big_batched_seed(self):
-        with open('seeds-big/my_seed.csv', 'w') as f:
-            writer = csv.writer(f)
-            writer.writerow(['id'])
-            for i in range(0, 20000):
-                writer.writerow([i])
-            
-        results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
-
-
-    @use_profile('postgres')
-    def test_postgres_big_batched_seed(self):
-        self.test_big_batched_seed()
-    

tests/adapter/dbt/tests/adapter/seed/data/seed.with.dots.csv

@@ -0,0 +1,2 @@
+seed_id
+1

tests/adapter/dbt/tests/adapter/seed/data/seed_actual.csv

@@ -1,4 +1,4 @@
-id,first_name,email,ip_address,birthday
+seed_id,first_name,email,ip_address,birthday
 1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
 2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
 3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57

tests/adapter/dbt/tests/adapter/seed/data/seed_bom.csv

@@ -1,4 +1,4 @@
-id,first_name,email,ip_address,birthday
+seed_id,first_name,email,ip_address,birthday
 1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
 2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
 3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57

tests/adapter/dbt/tests/adapter/seed/data/seed_expected.sql

@@ -1,5 +1,5 @@
 create table {schema}.seed_expected (
-	id INTEGER,
+	seed_id INTEGER,
 	first_name TEXT,
 	email TEXT,
 	ip_address TEXT,
@@ -8,7 +8,7 @@ create table {schema}.seed_expected (
 
 
 INSERT INTO {schema}.seed_expected
-    ("id","first_name","email","ip_address","birthday")
+    ("seed_id","first_name","email","ip_address","birthday")
 VALUES
     (1,'Larry','lking0@miitbeian.gov.cn','69.135.206.194','2008-09-12 19:08:31'),
     (2,'Larry','lperkins1@toplist.cz','64.210.133.162','1978-05-09 04:15:14'),

tests/adapter/dbt/tests/adapter/seed/data/seed_unicode.csv

@@ -1,2 +1,2 @@
-id
+seed_id
 Uh – Oh

tests/adapter/dbt/tests/adapter/seed/fixtures.py

@@ -0,0 +1,167 @@
+#
+# Seeds
+#
+
+seeds__enabled_in_config = """seed_id,first_name,email,ip_address,birthday
+1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
+2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
+3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57
+4,Sandra,sgeorge3@livejournal.com,229.235.252.98,1973-07-19 10:52:43
+5,Fred,fwoods4@google.cn,78.229.170.124,2012-09-30 16:38:29
+6,Stephen,shanson5@livejournal.com,182.227.157.105,1995-11-07 21:40:50
+7,William,wmartinez6@upenn.edu,135.139.249.50,1982-09-05 03:11:59
+8,Jessica,jlong7@hao123.com,203.62.178.210,1991-10-16 11:03:15
+9,Douglas,dwhite8@tamu.edu,178.187.247.1,1979-10-01 09:49:48
+10,Lisa,lcoleman9@nydailynews.com,168.234.128.249,2011-05-26 07:45:49
+11,Ralph,rfieldsa@home.pl,55.152.163.149,1972-11-18 19:06:11
+12,Louise,lnicholsb@samsung.com,141.116.153.154,2014-11-25 20:56:14
+13,Clarence,cduncanc@sfgate.com,81.171.31.133,2011-11-17 07:02:36
+14,Daniel,dfranklind@omniture.com,8.204.211.37,1980-09-13 00:09:04
+15,Katherine,klanee@auda.org.au,176.96.134.59,1997-08-22 19:36:56
+16,Billy,bwardf@wikia.com,214.108.78.85,2003-10-19 02:14:47
+17,Annie,agarzag@ocn.ne.jp,190.108.42.70,1988-10-28 15:12:35
+18,Shirley,scolemanh@fastcompany.com,109.251.164.84,1988-08-24 10:50:57
+19,Roger,rfrazieri@scribd.com,38.145.218.108,1985-12-31 15:17:15
+20,Lillian,lstanleyj@goodreads.com,47.57.236.17,1970-06-08 02:09:05
+
+"""
+
+seeds__disabled_in_config = """seed_id,first_name,email,ip_address,birthday
+1,Larry,lking0@miitbeian.gov.cn,69.135.206.194,2008-09-12 19:08:31
+2,Larry,lperkins1@toplist.cz,64.210.133.162,1978-05-09 04:15:14
+3,Anna,amontgomery2@miitbeian.gov.cn,168.104.64.114,2011-10-16 04:07:57
+4,Sandra,sgeorge3@livejournal.com,229.235.252.98,1973-07-19 10:52:43
+5,Fred,fwoods4@google.cn,78.229.170.124,2012-09-30 16:38:29
+6,Stephen,shanson5@livejournal.com,182.227.157.105,1995-11-07 21:40:50
+7,William,wmartinez6@upenn.edu,135.139.249.50,1982-09-05 03:11:59
+8,Jessica,jlong7@hao123.com,203.62.178.210,1991-10-16 11:03:15
+9,Douglas,dwhite8@tamu.edu,178.187.247.1,1979-10-01 09:49:48
+10,Lisa,lcoleman9@nydailynews.com,168.234.128.249,2011-05-26 07:45:49
+11,Ralph,rfieldsa@home.pl,55.152.163.149,1972-11-18 19:06:11
+12,Louise,lnicholsb@samsung.com,141.116.153.154,2014-11-25 20:56:14
+13,Clarence,cduncanc@sfgate.com,81.171.31.133,2011-11-17 07:02:36
+14,Daniel,dfranklind@omniture.com,8.204.211.37,1980-09-13 00:09:04
+15,Katherine,klanee@auda.org.au,176.96.134.59,1997-08-22 19:36:56
+16,Billy,bwardf@wikia.com,214.108.78.85,2003-10-19 02:14:47
+17,Annie,agarzag@ocn.ne.jp,190.108.42.70,1988-10-28 15:12:35
+18,Shirley,scolemanh@fastcompany.com,109.251.164.84,1988-08-24 10:50:57
+19,Roger,rfrazieri@scribd.com,38.145.218.108,1985-12-31 15:17:15
+20,Lillian,lstanleyj@goodreads.com,47.57.236.17,1970-06-08 02:09:05
+
+"""
+
+# used to tease out include/exclude edge case behavior for 'dbt seed'
+seeds__tricky = """\
+seed_id,seed_id_str,a_bool,looks_like_a_bool,a_date,looks_like_a_date,relative,weekday
+1,1,true,true,2019-01-01 12:32:30,2019-01-01 12:32:30,tomorrow,Saturday
+2,2,True,True,2019-01-01 12:32:31,2019-01-01 12:32:31,today,Sunday
+3,3,TRUE,TRUE,2019-01-01 12:32:32,2019-01-01 12:32:32,yesterday,Monday
+4,4,false,false,2019-01-01 01:32:32,2019-01-01 01:32:32,tomorrow,Saturday
+5,5,False,False,2019-01-01 01:32:32,2019-01-01 01:32:32,today,Sunday
+6,6,FALSE,FALSE,2019-01-01 01:32:32,2019-01-01 01:32:32,yesterday,Monday
+
+"""
+
+
+seeds__wont_parse = """a,b,c
+1,7,23,90,5
+2
+
+"""
+
+#
+# Macros
+#
+
+macros__schema_test = """
+{% test column_type(model, column_name, type) %}
+
+    {% set cols = adapter.get_columns_in_relation(model) %}
+
+    {% set col_types = {} %}
+    {% for col in cols %}
+        {% do col_types.update({col.name: col.data_type}) %}
+    {% endfor %}
+
+    {% set validation_message = 'Got a column type of ' ~ col_types.get(column_name) ~ ', expected ' ~ type %}
+
+    {% set val = 0 if col_types.get(column_name) == type else 1 %}
+    {% if val == 1 and execute %}
+        {{ log(validation_message, info=True) }}
+    {% endif %}
+
+    select '{{ validation_message }}' as validation_error
+    from (select true) as nothing
+    where {{ val }} = 1
+
+{% endtest %}
+
+"""
+
+#
+# Models
+#
+
+models__downstream_from_seed_actual = """
+select * from {{ ref('seed_actual') }}
+
+"""
+models__from_basic_seed = """
+select * from {{ this.schema }}.seed_expected
+
+"""
+
+#
+# Properties
+#
+
+properties__schema_yml = """
+version: 2
+seeds:
+- name: seed_enabled
+  columns:
+  - name: birthday
+    tests:
+    - column_type:
+        type: date
+  - name: seed_id
+    tests:
+    - column_type:
+        type: text
+
+- name: seed_tricky
+  columns:
+  - name: seed_id
+    tests:
+    - column_type:
+        type: integer
+  - name: seed_id_str
+    tests:
+    - column_type:
+        type: text
+  - name: a_bool
+    tests:
+    - column_type:
+        type: boolean
+  - name: looks_like_a_bool
+    tests:
+    - column_type:
+        type: text
+  - name: a_date
+    tests:
+    - column_type:
+        type: timestamp without time zone
+  - name: looks_like_a_date
+    tests:
+    - column_type:
+        type: text
+  - name: relative
+    tests:
+    - column_type:
+        type: text
+  - name: weekday
+    tests:
+    - column_type:
+        type: text
+
+"""

tests/adapter/dbt/tests/adapter/seed/test_seed.py

@@ -0,0 +1,311 @@
+import csv
+import pytest
+import shutil
+
+from codecs import BOM_UTF8
+from pathlib import Path
+
+from dbt.tests.util import (
+    run_dbt,
+    read_file,
+    check_relations_equal,
+    check_table_does_exist,
+    check_table_does_not_exist,
+)
+
+from dbt.tests.adapter.seed.fixtures import (
+    models__downstream_from_seed_actual,
+    models__from_basic_seed,
+    seeds__disabled_in_config,
+    seeds__enabled_in_config,
+    seeds__tricky,
+    seeds__wont_parse,
+)
+
+# from `test/integration/test_simple_seed`, test_simple_seed
+
+
+class SeedConfigBase(object):
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {
+                "quote_columns": False,
+            },
+        }
+
+
+class SeedTestBase(SeedConfigBase):
+    @pytest.fixture(scope="class", autouse=True)
+    def setUp(self, project):
+        """Create table for ensuring seeds and models used in tests build correctly"""
+        project.run_sql_file(project.test_data_dir / Path("seed_expected.sql"))
+
+    @pytest.fixture(scope="class")
+    def seeds(self, test_data_dir):
+        seed_actual_csv = read_file(test_data_dir, "seed_actual.csv")
+        return {"seed_actual.csv": seed_actual_csv}
+
+    @pytest.fixture(scope="class")
+    def models(self):
+        return {
+            "models__downstream_from_seed_actual.sql": models__downstream_from_seed_actual,
+        }
+
+    def _build_relations_for_test(self, project):
+        """The testing environment needs seeds and models to interact with"""
+        seed_result = run_dbt(["seed"])
+        assert len(seed_result) == 1
+        check_relations_equal(project.adapter, ["seed_expected", "seed_actual"])
+
+        run_result = run_dbt()
+        assert len(run_result) == 1
+        check_relations_equal(
+            project.adapter, ["models__downstream_from_seed_actual", "seed_expected"]
+        )
+
+    def _check_relation_end_state(self, run_result, project, exists: bool):
+        assert len(run_result) == 1
+        check_relations_equal(project.adapter, ["seed_actual", "seed_expected"])
+        if exists:
+            check_table_does_exist(project.adapter, "models__downstream_from_seed_actual")
+        else:
+            check_table_does_not_exist(project.adapter, "models__downstream_from_seed_actual")
+
+
+class BasicSeedTests(SeedTestBase):
+    def test_simple_seed(self, project):
+        """Build models and observe that run truncates a seed and re-inserts rows"""
+        self._build_relations_for_test(project)
+        self._check_relation_end_state(run_result=run_dbt(["seed"]), project=project, exists=True)
+
+    def test_simple_seed_full_refresh_flag(self, project):
+        """Drop the seed_actual table and re-create. Verifies correct behavior by the absence of the
+        model which depends on seed_actual."""
+        self._build_relations_for_test(project)
+        self._check_relation_end_state(
+            run_result=run_dbt(["seed", "--full-refresh"]), project=project, exists=False
+        )
+
+
+class SeedConfigFullRefreshOn(SeedTestBase):
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {"quote_columns": False, "full_refresh": True},
+        }
+
+    def test_simple_seed_full_refresh_config(self, project):
+        """config option should drop current model and cascade drop to downstream models"""
+        self._build_relations_for_test(project)
+        self._check_relation_end_state(run_result=run_dbt(["seed"]), project=project, exists=False)
+
+
+class SeedConfigFullRefreshOff(SeedTestBase):
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {"quote_columns": False, "full_refresh": False},
+        }
+
+    def test_simple_seed_full_refresh_config(self, project):
+        """Config options should override full-refresh flag because config is higher priority"""
+        self._build_relations_for_test(project)
+        self._check_relation_end_state(run_result=run_dbt(["seed"]), project=project, exists=True)
+        self._check_relation_end_state(
+            run_result=run_dbt(["seed", "--full-refresh"]), project=project, exists=True
+        )
+
+
+class SeedCustomSchema(SeedTestBase):
+    @pytest.fixture(scope="class", autouse=True)
+    def setUp(self, project):
+        """Create table for ensuring seeds and models used in tests build correctly"""
+        project.run_sql_file(project.test_data_dir / Path("seed_expected.sql"))
+
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {
+                "schema": "custom_schema",
+                "quote_columns": False,
+            },
+        }
+
+    def test_simple_seed_with_schema(self, project):
+        results = run_dbt(["seed"])
+        assert len(results) == 1
+        custom_schema = f"{project.test_schema}_custom_schema"
+        check_relations_equal(project.adapter, [f"{custom_schema}.seed_actual", "seed_expected"])
+
+        # this should truncate the seed_actual table, then re-insert
+        results = run_dbt(["seed"])
+        assert len(results) == 1
+        custom_schema = f"{project.test_schema}_custom_schema"
+        check_relations_equal(project.adapter, [f"{custom_schema}.seed_actual", "seed_expected"])
+
+    def test_simple_seed_with_drop_and_schema(self, project):
+        results = run_dbt(["seed"])
+        assert len(results) == 1
+        custom_schema = f"{project.test_schema}_custom_schema"
+        check_relations_equal(project.adapter, [f"{custom_schema}.seed_actual", "seed_expected"])
+
+        # this should drop the seed table, then re-create
+        results = run_dbt(["seed", "--full-refresh"])
+        custom_schema = f"{project.test_schema}_custom_schema"
+        check_relations_equal(project.adapter, [f"{custom_schema}.seed_actual", "seed_expected"])
+
+
+class SimpleSeedEnabledViaConfig(object):
+    @pytest.fixture(scope="session")
+    def seeds(self):
+        return {
+            "seed_enabled.csv": seeds__enabled_in_config,
+            "seed_disabled.csv": seeds__disabled_in_config,
+            "seed_tricky.csv": seeds__tricky,
+        }
+
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {
+                "test": {"seed_enabled": {"enabled": True}, "seed_disabled": {"enabled": False}},
+                "quote_columns": False,
+            },
+        }
+
+    @pytest.fixture(scope="function")
+    def clear_test_schema(self, project):
+        yield
+        project.run_sql(f"drop schema if exists {project.test_schema} cascade")
+
+    def test_simple_seed_with_disabled(self, clear_test_schema, project):
+        results = run_dbt(["seed"])
+        len(results) == 2
+        check_table_does_exist(project.adapter, "seed_enabled")
+        check_table_does_not_exist(project.adapter, "seed_disabled")
+        check_table_does_exist(project.adapter, "seed_tricky")
+
+    def test_simple_seed_selection(self, clear_test_schema, project):
+        results = run_dbt(["seed", "--select", "seed_enabled"])
+        len(results) == 1
+        check_table_does_exist(project.adapter, "seed_enabled")
+        check_table_does_not_exist(project.adapter, "seed_disabled")
+        check_table_does_not_exist(project.adapter, "seed_tricky")
+
+    def test_simple_seed_exclude(self, clear_test_schema, project):
+        results = run_dbt(["seed", "--exclude", "seed_enabled"])
+        len(results) == 1
+        check_table_does_not_exist(project.adapter, "seed_enabled")
+        check_table_does_not_exist(project.adapter, "seed_disabled")
+        check_table_does_exist(project.adapter, "seed_tricky")
+
+
+class SeedParsing(SeedConfigBase):
+    @pytest.fixture(scope="class", autouse=True)
+    def setUp(self, project):
+        """Create table for ensuring seeds and models used in tests build correctly"""
+        project.run_sql_file(project.test_data_dir / Path("seed_expected.sql"))
+
+    @pytest.fixture(scope="class")
+    def seeds(self):
+        return {"seed.csv": seeds__wont_parse}
+
+    @pytest.fixture(scope="class")
+    def models(self):
+        return {"model.sql": models__from_basic_seed}
+
+    def test_dbt_run_skips_seeds(self, project):
+        # run does not try to parse the seed files
+        len(run_dbt()) == 1
+
+        # make sure 'dbt seed' fails, otherwise our test is invalid!
+        run_dbt(["seed"], expect_pass=False)
+
+
+# BOM = byte order mark; see https://www.ibm.com/docs/en/netezza?topic=formats-byte-order-mark
+class SimpleSeedWithBOM(SeedConfigBase):
+    @pytest.fixture(scope="class", autouse=True)
+    def setUp(self, project):
+        """Create table for ensuring seeds and models used in tests build correctly"""
+        project.run_sql_file(project.test_data_dir / Path("seed_expected.sql"))
+
+        # manual copy because seed has a special and tricky-to-include unicode character at 0
+        shutil.copyfile(
+            project.test_data_dir / Path("seed_bom.csv"),
+            project.project_root / Path("seeds") / Path("seed_bom.csv"),
+        )
+
+    def test_simple_seed(self, project):
+        results = run_dbt(["seed"])
+        assert len(results) == 1
+
+        # encoding param must be specified in open, so long as Python reads files with a
+        # default file encoding for character sets beyond extended ASCII.
+        with open(
+            project.project_root / Path("seeds") / Path("seed_bom.csv"), encoding="utf-8"
+        ) as fp:
+            assert fp.read(1) == BOM_UTF8.decode("utf-8")
+
+        check_relations_equal(project.adapter, ["seed_expected", "seed_bom"])
+
+
+class SeedSpecificFormats(SeedConfigBase):
+    """Expect all edge cases to build"""
+
+    def _make_big_seed(self, test_data_dir):
+        big_seed_path = test_data_dir / Path("tmp.csv")
+        with open(big_seed_path, "w") as f:
+            writer = csv.writer(f)
+            writer.writerow(["seed_id"])
+            for i in range(0, 20000):
+                writer.writerow([i])
+        return big_seed_path
+
+    @pytest.fixture(scope="class")
+    def seeds(self, test_data_dir):
+        seed_unicode = read_file(test_data_dir, "seed_unicode.csv")
+        dotted_seed = read_file(test_data_dir, "seed.with.dots.csv")
+        big_seed = read_file(self._make_big_seed(test_data_dir))
+
+        return {
+            "big_seed.csv": big_seed,
+            "seed.with.dots.csv": dotted_seed,
+            "seed_unicode.csv": seed_unicode,
+        }
+
+    def test_simple_seed(self, project):
+        results = run_dbt(["seed"])
+        len(results) == 3
+
+
+class TestBasicSeedTests(BasicSeedTests):
+    pass
+
+
+class TestSeedConfigFullRefreshOn(SeedConfigFullRefreshOn):
+    pass
+
+
+class TestSeedConfigFullRefreshOff(SeedConfigFullRefreshOff):
+    pass
+
+
+class TestSeedCustomSchema(SeedCustomSchema):
+    pass
+
+
+class TestSimpleSeedEnabledViaConfig(SimpleSeedEnabledViaConfig):
+    pass
+
+
+class TestSeedParsing(SeedParsing):
+    pass
+
+
+class TestSimpleSeedWithBOM(SimpleSeedWithBOM):
+    pass
+
+
+class TestSeedSpecificFormats(SeedSpecificFormats):
+    pass

tests/adapter/dbt/tests/adapter/seed/test_seed_type_override.py

@@ -0,0 +1,70 @@
+import pytest
+
+from dbt.tests.util import run_dbt
+
+from dbt.tests.adapter.seed.fixtures import (
+    macros__schema_test,
+    properties__schema_yml,
+    seeds__disabled_in_config,
+    seeds__enabled_in_config,
+    seeds__tricky,
+)
+
+
+class SimpleSeedColumnOverride(object):
+    @pytest.fixture(scope="class")
+    def models(self):
+        return {
+            "schema.yml": properties__schema_yml,
+        }
+
+    @pytest.fixture(scope="class")
+    def seeds(self):
+        return {
+            "seed_enabled.csv": seeds__enabled_in_config,
+            "seed_disabled.csv": seeds__disabled_in_config,
+            "seed_tricky.csv": seeds__tricky,
+        }
+
+    @pytest.fixture(scope="class")
+    def macros(self):
+        return {"schema_test.sql": macros__schema_test}
+
+    @pytest.fixture(scope="class")
+    def project_config_update(self):
+        return {
+            "seeds": {
+                "test": {
+                    "enabled": False,
+                    "quote_columns": True,
+                    "seed_enabled": {"enabled": True, "+column_types": self.seed_enabled_types()},
+                    "seed_tricky": {
+                        "enabled": True,
+                        "+column_types": self.seed_tricky_types(),
+                    },
+                },
+            },
+        }
+
+    def seed_enabled_types(self):
+        return {
+            "seed_id": "text",
+            "birthday": "date",
+        }
+
+    def seed_tricky_types(self):
+        return {
+            "seed_id_str": "text",
+            "looks_like_a_bool": "text",
+            "looks_like_a_date": "text",
+        }
+
+    def test_simple_seed_with_column_override(self, project):
+        results = run_dbt(["seed", "--show"])
+        len(results) == 2
+        results = run_dbt(["test"])
+        len(results) == 10
+
+
+class TestSimpleSeedColumnOverride(SimpleSeedColumnOverride):
+    pass

tests/functional/simple_seed/test_seed.py

@@ -1,19 +0,0 @@
-import pytest
-from dbt.tests.util import run_dbt
-
-# from `test/integration/test_simple_seed`, test_postgres_simple_seed
-
-
-@pytest.fixture(scope="class")
-def project_config_update():
-    return {"seeds": {"quote_columns": False}}
-
-
-@pytest.fixture(scope="class")
-def seeds():
-    return {"data.csv": "a,b\n1,hello\n2,goodbye"}
-
-
-def test_simple_seed(project):
-    results = run_dbt(["seed"])
-    assert len(results) == 1