Skip to content

Commit

Permalink
Add new tests for new_record snapshot mode.
Browse files Browse the repository at this point in the history
  • Loading branch information
peterallenwebb committed Nov 22, 2024
1 parent ad575ec commit b05fcce
Show file tree
Hide file tree
Showing 2 changed files with 207 additions and 0 deletions.
85 changes: 85 additions & 0 deletions tests/functional/snapshots/data/seed_new_record_mode.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,85 @@
create table {database}.{schema}.seed (
id INTEGER,
first_name VARCHAR(50),
last_name VARCHAR(50),
email VARCHAR(50),
gender VARCHAR(50),
ip_address VARCHAR(20),
updated_at TIMESTAMP WITHOUT TIME ZONE
);

create table {database}.{schema}.snapshot_expected (
id INTEGER,
first_name VARCHAR(50),
last_name VARCHAR(50),
email VARCHAR(50),
gender VARCHAR(50),
ip_address VARCHAR(20),

-- snapshotting fields
updated_at TIMESTAMP WITHOUT TIME ZONE,
dbt_valid_from TIMESTAMP WITHOUT TIME ZONE,
dbt_valid_to TIMESTAMP WITHOUT TIME ZONE,
dbt_scd_id TEXT,
dbt_updated_at TIMESTAMP WITHOUT TIME ZONE,
dbt_is_deleted TEXT
);


-- seed inserts
-- use the same email for two users to verify that duplicated check_cols values
-- are handled appropriately
insert into {database}.{schema}.seed (id, first_name, last_name, email, gender, ip_address, updated_at) values
(1, 'Judith', 'Kennedy', '(not provided)', 'Female', '54.60.24.128', '2015-12-24 12:19:28'),
(2, 'Arthur', 'Kelly', '(not provided)', 'Male', '62.56.24.215', '2015-10-28 16:22:15'),
(3, 'Rachel', 'Moreno', '[email protected]', 'Female', '31.222.249.23', '2016-04-05 02:05:30'),
(4, 'Ralph', 'Turner', '[email protected]', 'Male', '157.83.76.114', '2016-08-08 00:06:51'),
(5, 'Laura', 'Gonzales', '[email protected]', 'Female', '30.54.105.168', '2016-09-01 08:25:38'),
(6, 'Katherine', 'Lopez', '[email protected]', 'Female', '169.138.46.89', '2016-08-30 18:52:11'),
(7, 'Jeremy', 'Hamilton', '[email protected]', 'Male', '231.189.13.133', '2016-07-17 02:09:46'),
(8, 'Heather', 'Rose', '[email protected]', 'Female', '87.165.201.65', '2015-12-29 22:03:56'),
(9, 'Gregory', 'Kelly', '[email protected]', 'Male', '154.209.99.7', '2016-03-24 21:18:16'),
(10, 'Rachel', 'Lopez', '[email protected]', 'Female', '237.165.82.71', '2016-08-20 15:44:49'),
(11, 'Donna', 'Welch', '[email protected]', 'Female', '103.33.110.138', '2016-02-27 01:41:48'),
(12, 'Russell', 'Lawrence', '[email protected]', 'Male', '189.115.73.4', '2016-06-11 03:07:09'),
(13, 'Michelle', 'Montgomery', '[email protected]', 'Female', '243.220.95.82', '2016-06-18 16:27:19'),
(14, 'Walter', 'Castillo', '[email protected]', 'Male', '71.159.238.196', '2016-10-06 01:55:44'),
(15, 'Robin', 'Mills', '[email protected]', 'Female', '172.190.5.50', '2016-10-31 11:41:21'),
(16, 'Raymond', 'Holmes', '[email protected]', 'Male', '148.153.166.95', '2016-10-03 08:16:38'),
(17, 'Gary', 'Bishop', '[email protected]', 'Male', '161.108.182.13', '2016-08-29 19:35:20'),
(18, 'Anna', 'Riley', '[email protected]', 'Female', '253.31.108.22', '2015-12-11 04:34:27'),
(19, 'Sarah', 'Knight', '[email protected]', 'Female', '222.220.3.177', '2016-09-26 00:49:06'),
(20, 'Phyllis', 'Fox', null, 'Female', '163.191.232.95', '2016-08-21 10:35:19');


-- populate snapshot table
insert into {database}.{schema}.snapshot_expected (
id,
first_name,
last_name,
email,
gender,
ip_address,
updated_at,
dbt_valid_from,
dbt_valid_to,
dbt_updated_at,
dbt_scd_id,
dbt_is_deleted
)

select
id,
first_name,
last_name,
email,
gender,
ip_address,
updated_at,
-- fields added by snapshotting
updated_at as dbt_valid_from,
null::timestamp as dbt_valid_to,
updated_at as dbt_updated_at,
md5(id || '-' || first_name || '|' || updated_at::text) as dbt_scd_id,
'False' as dbt_is_deleted
from {database}.{schema}.seed;
122 changes: 122 additions & 0 deletions tests/functional/snapshots/test_new_record_mode_snapshot.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,122 @@
import os

import pytest

from dbt.tests.util import check_relations_equal, run_dbt

snapshot_actual_sql = """
{% snapshot snapshot_actual %}
{{
config(
unique_key='id || ' ~ "'-'" ~ ' || first_name',
)
}}
select * from {{target.database}}.{{target.schema}}.seed
{% endsnapshot %}
"""

snapshots_yml = """
snapshots:
- name: snapshot_actual
config:
strategy: timestamp
updated_at: updated_at
hard_deletes: new_record
"""

ref_snapshot_sql = """
select * from {{ ref('snapshot_actual') }}
"""


invalidate_sql = """
-- update records 11 - 21. Change email and updated_at field
update {schema}.seed set
updated_at = updated_at + interval '1 hour',
email = case when id = 20 then '[email protected]' else 'new_' || email end
where id >= 10 and id <= 20;
-- invalidate records 11 - 21
update {schema}.snapshot_expected set
dbt_valid_to = updated_at + interval '1 hour'
where id >= 10 and id <= 20;
"""

update_sql = """
-- insert v2 of the 11 - 21 records
insert into {database}.{schema}.snapshot_expected (
id,
first_name,
last_name,
email,
gender,
ip_address,
updated_at,
dbt_valid_from,
dbt_valid_to,
dbt_updated_at,
dbt_scd_id,
dbt_is_deleted
)
select
id,
first_name,
last_name,
email,
gender,
ip_address,
updated_at,
-- fields added by snapshotting
updated_at as dbt_valid_from,
null::timestamp as dbt_valid_to,
updated_at as dbt_updated_at,
md5(id || '-' || first_name || '|' || updated_at::text) as dbt_scd_id,
'False' as dbt_is_deleted
from {database}.{schema}.seed
where id >= 10 and id <= 20;
"""

delete_sql = """
delete from {schema}.seed where id = 1
"""


class TestSnapshotNewRecordMode:
@pytest.fixture(scope="class")
def snapshots(self):
return {"snapshot.sql": snapshot_actual_sql}

@pytest.fixture(scope="class")
def models(self):
return {
"snapshots.yml": snapshots_yml,
"ref_snapshot.sql": ref_snapshot_sql,
}

def test_snapshot_new_record_mode(self, project):
path = os.path.join(project.test_data_dir, "seed_new_record_mode.sql")
project.run_sql_file(path)
results = run_dbt(["snapshot"])
assert len(results) == 1

project.run_sql(invalidate_sql)
project.run_sql(update_sql)

results = run_dbt(["snapshot"])
assert len(results) == 1

check_relations_equal(project.adapter, ["snapshot_actual", "snapshot_expected"])

project.run_sql(delete_sql)

results = run_dbt(["snapshot"])
assert len(results) == 1

# TODO: Further validate results.

0 comments on commit b05fcce

Please sign in to comment.