Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ python/

.vscode/
.idea/

.qodo/
# ==========================================
# Operating System Files
# ==========================================
Expand Down Expand Up @@ -108,4 +108,6 @@ docker-data/
# Misc Logs
# ==========================================

*.log
*.log
my_intro.md
mart_stracture.t
28 changes: 28 additions & 0 deletions macros/standardize_date.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
{% macro standardize_date(column_name) %}

CASE
WHEN TRIM({{ column_name }}) LIKE '[A-Z][a-z][a-z][a-z]% __, ____'
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}))

WHEN TRIM({{ column_name }}) LIKE '[A-Z][a-z][a-z] __, ____'
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}))

WHEN TRIM({{ column_name }}) LIKE '____-__-__'
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}))

WHEN TRIM({{ column_name }}) LIKE '____/__/__'
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}))

WHEN TRIM({{ column_name }}) LIKE '__/__/____'
AND TRY_CONVERT(INT, SUBSTRING(TRIM({{ column_name }}), 4, 2)) > 12
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}), 101)

WHEN TRIM({{ column_name }}) LIKE '__/__/____'
AND TRY_CONVERT(INT, LEFT(TRIM({{ column_name }}), 2)) > 12
THEN TRY_CONVERT(DATE, TRIM({{ column_name }}), 103)

ELSE TRY_CONVERT(DATE, TRIM({{ column_name }}), 101)

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Restore hyphenated date parsing before the fallback

When date_of_birth is in the existing dd-mm-yyyy/mm-dd-yyyy format, this macro now falls through to style 101; for values already present in scripts/raw_dataset/csv_data_file/raw_customers.csv such as 29-01-1982, SQL Server interprets the first component as the month and TRY_CONVERT returns NULL. The replaced inline CASE had explicit __-__-____ branches with styles 105/110, so this change silently drops those DOBs and then trips the existing not_null test. Restore the hyphenated branches before the fallback.

Useful? React with 👍 / 👎.


END

{% endmacro %}
4 changes: 2 additions & 2 deletions models/intermediate/Customers/_int__customers_models.yml
Original file line number Diff line number Diff line change
Expand Up @@ -67,8 +67,8 @@ models:
European, and month-name formats. Invalid or unrecognized values are
returned as NULL to preserve data quality while enabling accurate
age-based analysis and customer segmentation.
tests:
- not_null
# tests:
# - valid_date_format

#===================================================================================
#============================ Model: int_customers_contact =========================
Expand Down
28 changes: 15 additions & 13 deletions models/intermediate/Customers/int_customer_profile.sql
Original file line number Diff line number Diff line change
Expand Up @@ -36,18 +36,20 @@ SELECT
ELSE 'Unknown'
END as gender,

CASE
WHEN TRIM(date_of_birth) LIKE '[A-Z][a-z][a-z][a-z]% __, ____' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
WHEN TRIM(date_of_birth) LIKE '[A-Z][a-z][a-z] __, ____' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
WHEN TRIM(date_of_birth) LIKE '____-__-__' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
WHEN TRIM(date_of_birth) LIKE '____/__/__' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))

WHEN TRIM(date_of_birth) LIKE '__/__/____' AND TRY_CONVERT(INT, SUBSTRING(TRIM(date_of_birth), 4, 2)) > 12 THEN TRY_CONVERT(DATE, TRIM(date_of_birth), 101)
WHEN TRIM(date_of_birth) LIKE '__/__/____' AND TRY_CONVERT(INT, LEFT(TRIM(date_of_birth), 2)) > 12 THEN TRY_CONVERT(DATE , TRIM(date_of_birth), 103)

WHEN TRIM(date_of_birth) LIKE '__-__-____' AND TRY_CONVERT(INT, SUBSTRING(TRIM(date_of_birth), 4, 2)) > 12 THEN TRY_CONVERT(DATE, TRIM(date_of_birth), 110)
WHEN TRIM(date_of_birth) LIKE '__-__-____' AND TRY_CONVERT(INT, LEFT(TRIM(date_of_birth), 2)) > 12 THEN TRY_CONVERT(DATE , TRIM(date_of_birth), 105)
ELSE TRY_CONVERT(DATE, TRIM(date_of_birth), 101)
END date_of_birth
{{ standardize_date('date_of_birth') }} AS date_of_birth

--CASE
-- WHEN TRIM(date_of_birth) LIKE '[A-Z][a-z][a-z][a-z]% __, ____' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
-- WHEN TRIM(date_of_birth) LIKE '[A-Z][a-z][a-z] __, ____' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
-- WHEN TRIM(date_of_birth) LIKE '____-__-__' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))
-- WHEN TRIM(date_of_birth) LIKE '____/__/__' THEN TRY_CONVERT(DATE, TRIM(date_of_birth))

-- WHEN TRIM(date_of_birth) LIKE '__/__/____' AND TRY_CONVERT(INT, SUBSTRING(TRIM(date_of_birth), 4, 2)) > 12 THEN TRY_CONVERT(DATE, TRIM(date_of_birth), 101)
-- WHEN TRIM(date_of_birth) LIKE '__/__/____' AND TRY_CONVERT(INT, LEFT(TRIM(date_of_birth), 2)) > 12 THEN TRY_CONVERT(DATE , TRIM(date_of_birth), 103)

-- WHEN TRIM(date_of_birth) LIKE '__-__-____' AND TRY_CONVERT(INT, SUBSTRING(TRIM(date_of_birth), 4, 2)) > 12 THEN TRY_CONVERT(DATE, TRIM(date_of_birth), 110)
-- WHEN TRIM(date_of_birth) LIKE '__-__-____' AND TRY_CONVERT(INT, LEFT(TRIM(date_of_birth), 2)) > 12 THEN TRY_CONVERT(DATE , TRIM(date_of_birth), 105)
-- ELSE TRY_CONVERT(DATE, TRIM(date_of_birth), 101)
--END date_of_birth

FROM {{ ref('stg_customers') }} ;
11 changes: 11 additions & 0 deletions tests/generic/valid_date_format.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
{% test valid_date_of_birth(model, column_name) %}

SELECT *
FROM {{ model }}
WHERE {{ column_name }} IS NOT NULL
AND (
{{ column_name }} < '1900-01-01'
OR {{ column_name }} > CAST(GETDATE() AS DATE)
)

{% endtest %}
5 changes: 5 additions & 0 deletions tests/singular/valid_zip_code.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
SELECT *
FROM {{ ref('int_customer_location') }}
WHERE zip_code IS NULL
OR LEN(CAST(zip_code AS VARCHAR(10))) <> 5
OR TRY_CAST(zip_code AS INT) IS NULL
Loading