Create a python framework for multi-language generation

.github/workflows/black.yaml

@@ -0,0 +1,17 @@
+name: Lint
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.8 
+      - uses: psf/black@stable
+      - uses: jamescurtin/isort-action@master
+        with: 
+          requirementsFiles: "requirements.txt requirements-dev.txt"
+          configuration: "--check-only --diff --profile black"

.gitignore

@@ -0,0 +1,149 @@
+.idea
+src/awesome_date_dimension/.venv
+output/test
+test.py
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+- repo: https://github.com/psf/black
+  rev: 22.1.0
+  hooks:
+  - id: black
+- repo: https://github.com/pycqa/isort
+  rev: 5.10.1
+  hooks:
+    - id: isort
+      args: ["--profile", "black"]
+      name: isort (python)
+- repo: local
+  hooks:
+  - id: unittest
+    name: unittest
+    entry: python -m unittest discover -s tests
+    language: system
+    'types': [python]
+    pass_filenames: false
+    stages: [commit]

README.md

@@ -1,3 +1,5 @@
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
 # awesome-date-dimension
 
 A few months back, I had to create a date dimension. All of the scripts I could find publicly were missing a lot of the flags and other features I needed (especially around fiscal month handling) -- so I created one myself. This is written in T-SQL, but shouldn't be _too_ hard to port to another dialect of SQL.

awesome_date_dimension/_internal/tsql/dim_calendar_month_constraints_template.py

@@ -0,0 +1,11 @@
+from ...config import Config
+
+
+def dim_calendar_month_constraints_template(config: Config) -> str:
+    dcm_conf = config.dim_calendar_month
+    return f"""ALTER TABLE {dcm_conf.table_schema}.{dcm_conf.table_name}
+ADD PRIMARY KEY CLUSTERED ({dcm_conf.columns.month_start_key.name}, {dcm_conf.columns.month_end_key.name} ASC);
+
+CREATE NONCLUSTERED INDEX IDX_NC_{dcm_conf.table_schema}_{dcm_conf.table_name}_{dcm_conf.columns.month_start_date.name} ON {dcm_conf.table_schema}.{dcm_conf.table_name} ({dcm_conf.columns.month_start_date.name});
+CREATE NONCLUSTERED INDEX IDX_NC_{dcm_conf.table_schema}_{dcm_conf.table_name}_{dcm_conf.columns.month_end_date.name} ON {dcm_conf.table_schema}.{dcm_conf.table_name} ({dcm_conf.columns.month_end_date.name});
+"""

awesome_date_dimension/_internal/tsql/dim_calendar_month_insert_template.py

@@ -0,0 +1,148 @@
+from ...config import Config
+from .tsql_columns import TSQLDimCalendarMonthColumns
+
+
+def dim_calendar_month_insert_template(
+    config: Config, columns: TSQLDimCalendarMonthColumns
+) -> str:
+    dcm_conf = config.dim_calendar_month
+    dcm_cols = dcm_conf.columns
+    dd_conf = config.dim_date
+    dd_cols = dd_conf.columns
+    h_conf = config.holidays
+    holiday_columndef: list[str] = []
+    holiday_colselect: list[str] = []
+    if h_conf.generate_holidays:
+        for i, t in enumerate(h_conf.holiday_types):
+            holiday_columndef.append(
+                f"{t.generated_column_prefix}{t.generated_monthly_count_column_postfix} = SUM({t.generated_column_prefix}{t.generated_flag_column_postfix} * 1)"
+            )
+            holiday_colselect.append(
+                f"{t.generated_column_prefix}{t.generated_monthly_count_column_postfix}"
+            )
+
+        holiday_columndef_str = ",\n  ".join(holiday_columndef)
+    else:
+        holiday_columndef_str = ""
+
+    dcm_to_dd_colmap = {
+        dcm_cols.month_start_date.name: f"startdate.{dd_cols.the_date.name}",
+        dcm_cols.month_end_date.name: f"enddate.{dd_cols.the_date.name}",
+        dcm_cols.month_start_iso_date_name.name: f"startdate.{dd_cols.iso_date_name.name}",
+        dcm_cols.month_end_iso_date_name.name: f"enddate.{dd_cols.iso_date_name.name}",
+        dcm_cols.month_start_iso_week_date_name.name: f"startdate.{dd_cols.iso_week_date_name.name}",
+        dcm_cols.month_end_iso_week_date_name.name: f"enddate.{dd_cols.iso_week_date_name.name}",
+        dcm_cols.month_start_american_date_name.name: f"startdate.{dd_cols.american_date_name.name}",
+        dcm_cols.month_end_american_date_name.name: f"enddate.{dd_cols.american_date_name.name}",
+        dcm_cols.month_name.name: f"startdate.{dd_cols.month_name.name}",
+        dcm_cols.month_abbrev.name: f"startdate.{dd_cols.month_abbrev.name}",
+        dcm_cols.month_start_year_week_name.name: f"startdate.{dd_cols.year_week_name.name}",
+        dcm_cols.month_end_year_week_name.name: f"enddate.{dd_cols.year_week_name.name}",
+        dcm_cols.year_month_name.name: f"startdate.{dd_cols.year_month_name.name}",
+        dcm_cols.month_year_name.name: f"startdate.{dd_cols.month_year_name.name}",
+        dcm_cols.year_quarter_name.name: f"startdate.{dd_cols.year_quarter_name.name}",
+        dcm_cols.year.name: f"startdate.{dd_cols.year.name}",
+        dcm_cols.month_start_year_week.name: f"startdate.{dd_cols.year_week.name}",
+        dcm_cols.month_end_year_week.name: f"enddate.{dd_cols.year_week.name}",
+        dcm_cols.year_month.name: f"startdate.{dd_cols.year_month.name}",
+        dcm_cols.year_quarter.name: f"startdate.{dd_cols.year_quarter.name}",
+        dcm_cols.month_start_day_of_quarter.name: f"startdate.{dd_cols.day_of_quarter.name}",
+        dcm_cols.month_end_day_of_quarter.name: f"enddate.{dd_cols.day_of_quarter.name}",
+        dcm_cols.month_start_day_of_year.name: f"startdate.{dd_cols.day_of_year.name}",
+        dcm_cols.month_end_day_of_year.name: f"enddate.{dd_cols.day_of_year.name}",
+        dcm_cols.month_start_week_of_quarter.name: f"startdate.{dd_cols.week_of_quarter.name}",
+        dcm_cols.month_end_week_of_quarter.name: f"enddate.{dd_cols.week_of_quarter.name}",
+        dcm_cols.month_start_week_of_year.name: f"startdate.{dd_cols.week_of_year.name}",
+        dcm_cols.month_end_week_of_year.name: f"enddate.{dd_cols.week_of_year.name}",
+        dcm_cols.month_of_quarter.name: f"startdate.{dd_cols.month_of_quarter.name}",
+        dcm_cols.quarter.name: f"startdate.{dd_cols.quarter.name}",
+        dcm_cols.days_in_month.name: f"startdate.{dd_cols.days_in_month.name}",
+        dcm_cols.days_in_quarter.name: f"startdate.{dd_cols.days_in_quarter.name}",
+        dcm_cols.days_in_year.name: f"startdate.{dd_cols.days_in_year.name}",
+        dcm_cols.current_month_flag.name: f"startdate.{dd_cols.current_month_flag.name}",
+        dcm_cols.prior_month_flag.name: f"startdate.{dd_cols.prior_month_flag.name}",
+        dcm_cols.next_month_flag.name: f"startdate.{dd_cols.next_month_flag.name}",
+        dcm_cols.current_quarter_flag.name: f"startdate.{dd_cols.current_quarter_flag.name}",
+        dcm_cols.prior_quarter_flag.name: f"startdate.{dd_cols.prior_quarter_flag.name}",
+        dcm_cols.next_quarter_flag.name: f"startdate.{dd_cols.next_quarter_flag.name}",
+        dcm_cols.current_year_flag.name: f"startdate.{dd_cols.current_year_flag.name}",
+        dcm_cols.prior_year_flag.name: f"startdate.{dd_cols.prior_year_flag.name}",
+        dcm_cols.next_year_flag.name: f"startdate.{dd_cols.next_year_flag.name}",
+        dcm_cols.first_day_of_month_flag.name: f"startdate.{dd_cols.first_day_of_month_flag.name}",
+        dcm_cols.last_day_of_month_flag.name: f"startdate.{dd_cols.last_day_of_month_flag.name}",
+        dcm_cols.first_day_of_quarter_flag.name: f"startdate.{dd_cols.first_day_of_quarter_flag.name}",
+        dcm_cols.last_day_of_quarter_flag.name: f"startdate.{dd_cols.last_day_of_quarter_flag.name}",
+        dcm_cols.first_day_of_year_flag.name: f"startdate.{dd_cols.first_day_of_year_flag.name}",
+        dcm_cols.last_day_of_year_flag.name: f"startdate.{dd_cols.last_day_of_year_flag.name}",
+        dcm_cols.month_start_fraction_of_quarter.name: f"startdate.{dd_cols.fraction_of_quarter.name}",
+        dcm_cols.month_end_fraction_of_quarter.name: f"enddate.{dd_cols.fraction_of_quarter.name}",
+        dcm_cols.month_start_fraction_of_year.name: f"startdate.{dd_cols.fraction_of_year.name}",
+        dcm_cols.month_end_fraction_of_year.name: f"enddate.{dd_cols.fraction_of_year.name}",
+        dcm_cols.current_quarter_start.name: f"startdate.{dd_cols.current_quarter_start.name}",
+        dcm_cols.current_quarter_end.name: f"startdate.{dd_cols.current_quarter_end.name}",
+        dcm_cols.current_year_start.name: f"startdate.{dd_cols.current_year_start.name}",
+        dcm_cols.current_year_end.name: f"startdate.{dd_cols.current_year_end.name}",
+        dcm_cols.prior_month_start.name: f"startdate.{dd_cols.prior_month_start.name}",
+        dcm_cols.prior_month_end.name: f"startdate.{dd_cols.prior_month_end.name}",
+        dcm_cols.prior_quarter_start.name: f"startdate.{dd_cols.prior_quarter_start.name}",
+        dcm_cols.prior_quarter_end.name: f"startdate.{dd_cols.prior_quarter_end.name}",
+        dcm_cols.prior_year_start.name: f"startdate.{dd_cols.prior_year_start.name}",
+        dcm_cols.prior_year_end.name: f"startdate.{dd_cols.prior_year_end.name}",
+        dcm_cols.next_month_start.name: f"startdate.{dd_cols.next_month_start.name}",
+        dcm_cols.next_month_end.name: f"startdate.{dd_cols.next_month_end.name}",
+        dcm_cols.next_quarter_start.name: f"startdate.{dd_cols.next_quarter_start.name}",
+        dcm_cols.next_quarter_end.name: f"startdate.{dd_cols.next_quarter_end.name}",
+        dcm_cols.next_year_start.name: f"startdate.{dd_cols.next_year_start.name}",
+        dcm_cols.next_year_end.name: f"startdate.{dd_cols.next_year_end.name}",
+        dcm_cols.month_start_quarterly_burnup.name: f"startdate.{dd_cols.quarterly_burnup.name}",
+        dcm_cols.month_end_quarterly_burnup.name: f"enddate.{dd_cols.quarterly_burnup.name}",
+        dcm_cols.month_start_yearly_burnup.name: f"startdate.{dd_cols.yearly_burnup.name}",
+        dcm_cols.month_end_yearly_burnup.name: f"enddate.{dd_cols.yearly_burnup.name}",
+    }
+
+    insert_columns_clause = ",\n  ".join((c.name for c in columns))
+    select_columns = []
+    for col in columns:
+        if (dd_name := dcm_to_dd_colmap.get(col.name)) is not None:
+            select_columns.append(f"{col.name} = {dd_name}")
+        else:
+            select_columns.append(f"{col.name} = base.{col.name}")
+
+    select_columns_clause = ",\n  ".join(select_columns)
+
+    return f"""WITH DistinctMonths AS (
+  SELECT
+  {dcm_cols.month_start_key.name} = CONVERT(
+    int,
+    CONVERT(
+    varchar(8),
+    {dd_cols.current_month_start.name},
+    112
+    )
+  ),
+  {dcm_cols.month_end_key.name} = CONVERT(
+    int,
+    CONVERT(
+    varchar(8),
+    {dd_cols.current_month_end.name},
+    112
+    )
+  ),
+  {holiday_columndef_str}
+  FROM
+    {dd_conf.table_schema}.{dd_conf.table_name}
+    GROUP BY {dd_cols.current_month_start.name}, {dd_cols.current_month_end.name}
+)
+
+INSERT INTO {dcm_conf.table_schema}.{dcm_conf.table_name} (
+  {insert_columns_clause}
+)
+-- Yank the day-level stuff we need for both the start and end dates from {dd_conf.table_name}
+SELECT  
+  {select_columns_clause}
+FROM
+  DistinctMonths AS base
+  INNER JOIN {dd_conf.table_schema}.{dd_conf.table_name} AS startdate
+    ON base.{dcm_cols.month_start_key.name} = startdate.{dd_cols.date_key.name}
+  INNER JOIN {dd_conf.table_schema}.{dd_conf.table_name} AS enddate
+    ON base.{dcm_cols.month_end_key.name} = enddate.{dd_cols.date_key.name};"""

awesome_date_dimension/_internal/tsql/dim_calendar_month_refresh_template.py

@@ -0,0 +1,39 @@
+from ...config import Config
+from .dim_calendar_month_insert_template import dim_calendar_month_insert_template
+from .tsql_columns import TSQLDimCalendarMonthColumns
+
+
+def dim_calendar_month_refresh_template(
+    config: Config, columns: TSQLDimCalendarMonthColumns
+) -> str:
+    indentation_level = "    "
+    insert_script = dim_calendar_month_insert_template(config, columns)
+    indented_script = "\n".join(
+        map(lambda line: indentation_level + line, insert_script.split("\n"))
+    )
+    return f"""CREATE PROCEDURE dbo.sp_build_DimCalendarMonth AS BEGIN
+  SET XACT_ABORT ON;
+  BEGIN TRY
+    BEGIN TRANSACTION;
+
+    TRUNCATE TABLE dbo.DimCalendarMonth;
+
+{indented_script}
+
+    COMMIT TRANSACTION;
+  END TRY
+  BEGIN CATCH
+    SELECT   
+      ERROR_NUMBER() AS ErrorNumber,
+      ERROR_SEVERITY() AS ErrorSeverity,
+      ERROR_STATE() AS ErrorState,
+      ERROR_LINE () AS ErrorLine,
+      ERROR_PROCEDURE() AS ErrorProcedure,
+      ERROR_MESSAGE() AS ErrorMessage;
+    IF @@TRANCOUNT > 0
+      ROLLBACK TRANSACTION;
+    THROW;
+  END CATCH;
+END
+GO
+"""