data-manipulation 0.53__tar.gz → 0.55__tar.gz

{data_manipulation-0.53 → data_manipulation-0.55}/.github/ISSUE_TEMPLATE/bug_report.md

@@ -12,6 +12,7 @@ A clear and concise description of what the bug is.
 
 **To Reproduce**
 Steps to reproduce the behavior:
+
 1. Go to '...'
 2. Click on '....'
 3. Scroll down to '....'
@@ -24,15 +25,17 @@ A clear and concise description of what you expected to happen.
 If applicable, add screenshots to help explain your problem.
 
 **Desktop (please complete the following information):**
- - OS: [e.g. iOS]
- - Browser [e.g. chrome, safari]
- - Version [e.g. 22]
+
+- OS: [e.g. iOS]
+- Browser [e.g. chrome, safari]
+- Version [e.g. 22]
 
 **Smartphone (please complete the following information):**
- - Device: [e.g. iPhone6]
- - OS: [e.g. iOS8.1]
- - Browser [e.g. stock browser, safari]
- - Version [e.g. 22]
+
+- Device: [e.g. iPhone6]
+- OS: [e.g. iOS8.1]
+- Browser [e.g. stock browser, safari]
+- Version [e.g. 22]
 
 **Additional context**
 Add any other context about the problem here.

data_manipulation-0.55/.gitignore

@@ -0,0 +1,229 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+*.lcov
+.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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# custom
+.claude
+.opencode
+.specstory
+.vscode
+AGENTS.md
+CLAUDE.md
+data_manipulation/_version.py

{data_manipulation-0.53 → data_manipulation-0.55}/CHANGELOG.md

@@ -4,29 +4,40 @@
 
 ### Removed
 
-- **`pandas_.clean_none()`** — function has been removed.
+- **`django_` module** - removed entirely (breaking change). The Django helpers
+  (`init_django`, `get_django_countries_dict`, `django_validate_email`,
+  `django_validate_url`, `django_validate_phone`) now live in the
+  [`django-util`](https://github.com/shawnngtq/django-util) package:
+  `django_util.utility` (`init_django`, `get_django_countries_dict`) and
+  `django_util.validators` (the `django_validate_*` functions). `data_manipulation`
+  no longer depends on Django. This warrants a major version bump on release.
+
+- **`pandas_.clean_none()`** - function has been removed.
   Migrate to pandas built-ins:
+
   ```python
   df = df.replace(r"^\s*$", np.nan, regex=True)
   df = df.where(pd.notnull(df), None)
   ```
 
-- **`pandas_.config_pandas_display()`** — function has been removed.
+- **`pandas_.config_pandas_display()`** - function has been removed.
   Set display options directly:
+
   ```python
   pd.set_option("display.max_columns", 500)
   pd.set_option("display.max_colwidth", 500)
   pd.set_option("display.expand_frame_repr", True)
   ```
 
-- **`prometheus_` module** — was an empty placeholder; removed from
+- **`prometheus_` module** - was an empty placeholder; removed from
   the public API and from `__init__` imports.
 
 ### Changed
 
-- **`base.get_none_variation()`** — now returns a `frozenset` of 7
+- **`base.get_none_variation()`** - now returns a `frozenset` of 7
   lowercase canonical strings instead of a 72-item list of case
   permutations. Use `.casefold()` for membership checks:
+
   ```python
   # before
   if value in get_none_variation():
@@ -36,46 +47,46 @@
       ...
   ```
 
-- **`pyspark_.group_count()`** — the `percent` column is now computed
+- **`pyspark_.group_count()`** - the `percent` column is now computed
   as a native Spark column expression instead of a Python UDF.
   Behaviour is identical; performance improves on large datasets.
 
-- **`pyspark_.column_into_list()`** — raises `ValueError` (with the
+- **`pyspark_.column_into_list()`** - raises `ValueError` (with the
   list of available columns) when the requested column does not exist.
   Previously returned `None` silently.
 
-- **`pandas_.print_dataframe_overview()`** — now returns a
+- **`pandas_.print_dataframe_overview()`** - now returns a
   `Dict[str, Dict[str, Any]]` of per-column stats (`unique`,
   `null_count`, `value_counts`). Still prints to stdout as before;
   existing call sites are unaffected.
 
-- **`pandas_.compare_dataframes()`** — now returns a comparison
+- **`pandas_.compare_dataframes()`** - now returns a comparison
   summary dict (`same_length`, `df1_length`, `df2_length`, `columns`).
   Still prints to stdout as before; existing call sites are unaffected.
 
-- **`pyspark_` module** — all `print()` calls replaced with
+- **`pyspark_` module** - all `print()` calls replaced with
   `logger.info()` / `logger.debug()`. Output is now routed through
   the standard logging pipeline and can be silenced or redirected.
 
-- **`sqlalchemy_.create_sqlalchemy_engine()`** — duplicate
+- **`sqlalchemy_.create_sqlalchemy_engine()`** - duplicate
   `if/elif` timeout branches (both setting the same value) consolidated
   into a single condition.
 
-- **`django_.django_validate_phone()`** — now has an explicit
+- **`django_.django_validate_phone()`** - now has an explicit
   `return None` on failure instead of a bare `return`.
 
-### Fixed (previous pass — reference)
+### Fixed (previous pass - reference)
 
-- `pyspark_.columns_statistics()` — always-true condition in empty-column
+- `pyspark_.columns_statistics()` - always-true condition in empty-column
   detection (third clause was truthy for any non-empty string).
-- `pandas_.dtypes_dictionary()` — `.iteritems()` removed in pandas 2.0;
+- `pandas_.dtypes_dictionary()` - `.iteritems()` removed in pandas 2.0;
   replaced with `.items()`.
 - Bare `except:` replaced with `except Exception:` in `pandas_` and
   `django_`.
-- `base.string_boolean_to_int()` — removed (used `distutils`, dropped
+- `base.string_boolean_to_int()` - removed (used `distutils`, dropped
   in Python 3.12).
-- `flask_.py` — deleted (was entirely commented-out dead code).
-- `beautifulsoup_.preprocess()` — fixed mixed tabs/spaces and invalid
+- `flask_.py` - deleted (was entirely commented-out dead code).
+- `beautifulsoup_.preprocess()` - fixed mixed tabs/spaces and invalid
   `\s` escape sequences.
 - All modules now guard third-party imports with `try/except`; the
   package imports cleanly even when optional dependencies are missing.

{data_manipulation-0.53 → data_manipulation-0.55}/CODE_OF_CONDUCT.md

@@ -23,13 +23,16 @@ include:
 Examples of unacceptable behavior by participants include:
 
 * The use of sexualized language or imagery and unwelcome sexual attention or
- advances
+
+  advances
 * Trolling, insulting/derogatory comments, and personal or political attacks
 * Public or private harassment
 * Publishing others' private information, such as a physical or electronic
- address, without explicit permission
+
+  address, without explicit permission
 * Other conduct which could reasonably be considered inappropriate in a
- professional setting
+
+  professional setting
 
 ## Our Responsibilities
 
@@ -55,7 +58,7 @@ further defined and clarified by project maintainers.
 ## Enforcement
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at Shawn.coding.acc@gmail.com. All
+reported by contacting the project team at <Shawn.coding.acc@gmail.com>. All
 complaints will be reviewed and investigated and will result in a response that
 is deemed necessary and appropriate to the circumstances. The project team is
 obligated to maintain confidentiality with regard to the reporter of an incident.
@@ -68,9 +71,9 @@ members of the project's leadership.
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+available at <https://www.contributor-covenant.org/version/1/4/code-of-conduct.html>
 
 [homepage]: https://www.contributor-covenant.org
 
 For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
+<https://www.contributor-covenant.org/faq>

{data_manipulation-0.53 → data_manipulation-0.55}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data_manipulation
-Version: 0.53
+Version: 0.55
 Summary: Powerful data manipulation
 Author-email: Shawn Ng <shawn.coding.acc@gmail.com>
 License-Expression: BSD-3-Clause
@@ -10,30 +10,30 @@ Classifier: Environment :: Console
 Classifier: Operating System :: OS Independent
 Classifier: Intended Audience :: Science/Research
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Cython
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: >=3.9
+Requires-Python: >=3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: beautifulsoup4
 Requires-Dist: boto3
 Requires-Dist: cryptography
-Requires-Dist: django
 Requires-Dist: flask
-Requires-Dist: geopandas
 Requires-Dist: ipython
 Requires-Dist: loguru
 Requires-Dist: mysql-connector-python
 Requires-Dist: numpy
 Requires-Dist: pandas
+Requires-Dist: polars
 Requires-Dist: psycopg
+Requires-Dist: pyiceberg
 Requires-Dist: pyspark
 Requires-Dist: python-dotenv
 Requires-Dist: sqlalchemy
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-mock; extra == "test"
 Dynamic: license-file
 
 # Data Manipulation
@@ -56,7 +56,7 @@ Data Manipulation is a Python package providing powerful utility functions. It c
 
 ## Where to get it
 
-The source code is currently hosted on GitHub at: https://github.com/shawnngtq/data-manipulation
+The source code is currently hosted on GitHub at: <https://github.com/shawnngtq/data-manipulation>
 
 ```bash
 pip install data-manipulation

{data_manipulation-0.53 → data_manipulation-0.55}/README.md

@@ -18,7 +18,7 @@ Data Manipulation is a Python package providing powerful utility functions. It c
 
 ## Where to get it
 
-The source code is currently hosted on GitHub at: https://github.com/shawnngtq/data-manipulation
+The source code is currently hosted on GitHub at: <https://github.com/shawnngtq/data-manipulation>
 
 ```bash
 pip install data-manipulation

{data_manipulation-0.53 → data_manipulation-0.55}/RELEASE.md

@@ -20,6 +20,16 @@ git status
 
 `git status` should report no changes before continuing.
 
+## Local Development Build
+
+Contributors do not need PyPI credentials or this release flow. To work on the package
+locally, install it editable and build with the standard tooling:
+
+```bash
+pip install -e .
+python -m build          # or: uv build
+```
+
 ## Tag The Release
 
 Use the next release version, for example `0.50`:
@@ -34,13 +44,17 @@ The tag must point at the exact commit being released.
 
 ## Publish Documentation
 
-Build the MkDocs documentation:
+Both commands require an environment that provides `mkdocs`, `mkdocs-material`, and
+`mkdocstrings-python` (for example a virtualenv, conda env, or pixi shell). Activate that
+environment before running them.
+
+Build the MkDocs documentation (local preview only):
 
 ```bash
 mkdocs build
 ```
 
-Publish the generated HTML to GitHub Pages:
+Deploy to GitHub Pages:
 
 ```bash
 mkdocs gh-deploy
@@ -48,18 +62,38 @@ mkdocs gh-deploy
 
 This publishes the contents of `site/` to the `gh-pages` branch.
 
+**Note - documentation and PyPI releases are independent.**
+
+- **Tags are only for PyPI releases.** `setuptools-scm` derives the package
+  version from git tags. Create a tag only when the shipped `data_manipulation/`
+  package changes; tooling- or docs-only changes need no tag.
+- **Docs deploy without a tag.** `deploy_docs` publishes current `master` to the
+  separate `gh-pages` branch, independent of any tag or PyPI release.
+- **Commit and push doc/source changes to `master` before building.** The site
+  renders the working tree, and `create_update_docs` writes only to the
+  gitignored `site/` directory - no tracked files change.
+- **When cutting a release, build docs after tagging** so the published site
+  matches the released commit.
+
 ## Publish To PyPI
 
+Build from a **clean checkout of the tagged commit** so the artifacts carry the tag
+version. `setuptools-scm` derives the version from git, so any uncommitted tracked change
+makes it emit the *next* version as `<next>.devN+d<date>` instead of the tag - confirm
+`git status` is clean before building.
+
 Build and validate the distribution artifacts:
 
 ```bash
-./setup.sh cleanup
+rm -rf build dist ./*.egg-info
+python -m build
+python -m twine check --strict dist/*
 ```
 
 Upload the artifacts:
 
 ```bash
-./setup.sh upload
+python -m twine upload dist/*
 ```
 
 When prompted by `twine`, enter the PyPI API token. The token should start with

data_manipulation-0.55/conftest.py

@@ -0,0 +1,24 @@
+"""Repo-root pytest configuration.
+
+``--doctest-modules`` (see ``[tool.pytest.ini_options]``) collects doctests from
+every ``data_manipulation/*.py``. We only want to *execute* examples that are
+robustly runnable, so ignore the rest here. Their ``Examples:`` blocks still
+render in the mkdocs API reference — they are just not auto-verified.
+
+Auto-verified modules (not ignored): base.py, beautifulsoup_.py, sqlalchemy_.py.
+"""
+
+collect_ignore = [
+    "data_manipulation/__init__.py",
+    "data_manipulation/_version.py",
+    "data_manipulation/pandas_.py",
+    "data_manipulation/pyspark_.py",
+    "data_manipulation/boto3_.py",
+    "data_manipulation/kerberos_.py",
+    "data_manipulation/openldap_.py",
+    "data_manipulation/cryptography_.py",
+    "data_manipulation/mysql_connector_python_.py",
+    "data_manipulation/postgres_.py",
+    "data_manipulation/smtplib_.py",
+    "data_manipulation/polars_.py",
+]

{data_manipulation-0.53 → data_manipulation-0.55}/data_manipulation/__init__.py

@@ -3,8 +3,7 @@ from data_manipulation import (
     beautifulsoup_,
     boto3_,
     cryptography_,
-    django_,
-    geopandas_,
+    iceberg,
     kerberos_,
     mysql_connector_python_,
     openldap_,

{data_manipulation-0.53 → data_manipulation-0.55}/data_manipulation/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.53'
-__version_tuple__ = version_tuple = (0, 53)
+__version__ = version = '0.55'
+__version_tuple__ = version_tuple = (0, 55)
 
-__commit_id__ = commit_id = 'g2446c213a'
+__commit_id__ = commit_id = 'gb82db140a'