clearspark 0.0.1__tar.gz

clearspark-0.0.1/.gitignore

@@ -0,0 +1,218 @@
+# 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
+.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
+
+# 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

clearspark-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Vinicius de Oliveira
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

clearspark-0.0.1/PKG-INFO

@@ -0,0 +1,53 @@
+Metadata-Version: 2.4
+Name: clearspark
+Version: 0.0.1
+Summary: A curated collection of essential PySpark functions for daily data engineering.
+Project-URL: Repository, https://github.com/v-skolder/clearspark
+Project-URL: owner, https://github.com/v-skolder
+Author-email: Vinicius <vinnyuniverso3@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: bucketing,categorization,data-engineering,dataframe,etl,pyspark,spark-utils
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.8
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyspark>=3.5.0
+Provides-Extra: dev
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Description-Content-Type: text/markdown
+
+<img src="docs/assets/images/readme-logo.png"/>
+
+# clearspark
+
+**clearspark** is a lightweight PySpark utility library that makes common data transformation patterns cleaner, faster to write, and easier to read. Stop rewriting the same boilerplate `when/otherwise` chains — clearspark gives you expressive, validated, one-liner functions.
+
+**[Function reference →](docs/functions.md)**
+
+---
+
+## Installation
+
+```bash
+pip install git+https://github.com/v-skolder/clearspark.git
+```
+
+---
+
+## Importing
+
+```python
+import clearspark.functions as cf
+```

clearspark-0.0.1/README.md

@@ -0,0 +1,23 @@
+<img src="docs/assets/images/readme-logo.png"/>
+
+# clearspark
+
+**clearspark** is a lightweight PySpark utility library that makes common data transformation patterns cleaner, faster to write, and easier to read. Stop rewriting the same boilerplate `when/otherwise` chains — clearspark gives you expressive, validated, one-liner functions.
+
+**[Function reference →](docs/functions.md)**
+
+---
+
+## Installation
+
+```bash
+pip install git+https://github.com/v-skolder/clearspark.git
+```
+
+---
+
+## Importing
+
+```python
+import clearspark.functions as cf
+```

clearspark-0.0.1/pyproject.toml

@@ -0,0 +1,58 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "clearspark"
+version = "0.0.1"
+description = "A curated collection of essential PySpark functions for daily data engineering."
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "MIT"}
+keywords = ["pyspark", "data-engineering", "dataframe", "etl", "spark-utils", "bucketing", "categorization"]
+authors = [
+    {name = "Vinicius", email = "vinnyuniverso3@gmail.com"},
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "pyspark>=3.5.0",
+    "pydantic>=2.0"
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "pytest-cov",
+]
+
+[project.urls]
+Repository = "https://github.com/v-skolder/clearspark"
+owner = "https://github.com/v-skolder"
+
+[tool.hatch.build.targets.sdist]
+include = ["/src"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/clearspark"]
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

clearspark-0.0.1/src/clearspark/__init__.py

@@ -0,0 +1,4 @@
+
+__all__ = [
+    'functions'
+]

clearspark-0.0.1/src/clearspark/annotations.py

@@ -0,0 +1,48 @@
+
+from typing import (
+    Annotated, 
+    Any, 
+    Optional
+)
+
+from pydantic import BeforeValidator
+
+__all__ = ["DuckSparkSession", "DuckSparkDataFrame", "DuckSparkColumn"]
+
+# UTILS
+
+def _hasattrs(v: Any, required_attr: list[str]) -> bool:
+    return all(hasattr(v, attr) for attr in required_attr)
+
+
+# VALIDATE FUNCTIONS
+
+def validate_spark_session(v: Any) -> Any:
+    required_attr = ["read", "createDataFrame", "table", "catalog"]
+
+    if not _hasattrs(v, required_attr) and v is not None:
+        raise ValueError(f"Invalid SparkSession-like object: {type(v).__name__}")
+
+    return v
+
+
+def validate_spark_dataframe(v: Any) -> Any:
+    required_attr = ["select", "columns", "filter", "groupBy", "withColumn"]
+
+    if not _hasattrs(v, required_attr):
+        raise ValueError(f"Invalid Dataframe-like object: {type(v).__name__}")
+
+
+def validate_spark_column(v: Any) -> Any:
+    required_attr = ["alias", "cast", "desc", "asc"]
+
+    if not _hasattrs(v, required_attr):
+        raise ValueError(f"Invalid Column-like object: {type(v).__name__}")
+
+# ANNOTATIONS
+
+DuckSparkSession = Optional[Annotated[Any, BeforeValidator(validate_spark_session)]]
+
+DuckSparkDataFrame = Annotated[Any, BeforeValidator(validate_spark_dataframe)]
+
+DuckSparkColumn = Annotated[Any, BeforeValidator(validate_spark_column)]

clearspark-0.0.1/src/clearspark/functions.py

@@ -0,0 +1,129 @@
+
+from clearspark.annotations import (
+    DuckSparkColumn, 
+    DuckSparkSession,
+    DuckSparkDataFrame
+)
+
+from typing import (
+    Optional, 
+    Union
+)
+
+from pydantic import (
+    ConfigDict, 
+    validate_call
+)
+
+from pyspark.sql import (
+    DataFrame, 
+    SparkSession
+)
+
+__all__ = [
+    "load_data",
+    "save_data"
+]
+
+# UTILS
+
+def _is_catalog_path(path: str):
+    return '/' not in path
+
+# FUNCTIONS
+
+@validate_call(config=ConfigDict(arbitrary_types_allowed=True))
+def load_data(
+    path: str,
+    format: str = "delta",
+    select_cols: Optional[Union[list[str], list[DuckSparkColumn]]] = None,
+    filter_spec: Optional[Union[str, DuckSparkColumn]] = None,
+    spark_session: Optional[DuckSparkSession] = None,
+) -> DataFrame:
+    """Loads a DataFrame from a catalog table or file path.
+
+    Reads data using the given format, optionally selecting specific
+    columns and applying a filter. The source is resolved as a catalog
+    table if `path` contains no "/", otherwise as a file path.
+
+    Args:
+        path: Catalog table name (e.g. "db.table") or file path
+            (e.g. "/data/events").
+        format: Data source format. Defaults to "delta".
+        select_cols: Columns to select, as column names or
+            `DuckSparkColumn` expressions. If None, all columns are
+            returned.
+        filter_spec: Filter condition as a SQL string or a
+            `DuckSparkColumn` expression. If None, no filter is applied.
+        spark_session: Session to use. If None, the active
+            `SparkSession` is used.
+
+    Returns:
+        A `DataFrame` with the loaded (and optionally filtered/selected)
+        data.
+
+    Raises:
+        ValueError: If no active Spark session is found and
+            `spark_session` is not provided.
+
+    Example:
+        >>> load_data("db.events", select_cols=["id", "ts"])
+        >>> load_data("/data/events", format="parquet", filter_spec="ts > 0")
+    """
+
+    reader = (spark_session or SparkSession.getActiveSession()).read.format(format)
+
+    df = reader.table(path) if _is_catalog_path else reader.load(path)
+
+    if select_cols is not None:
+        df = df.select(select_cols)
+
+    if filter_spec is not None:
+        df = df.filter(filter_spec)
+
+    return df
+
+@validate_call(config=ConfigDict(arbitrary_types_allowed=True))
+def save_data(
+        df: DuckSparkDataFrame,
+        data_path: str,
+        data_format: str = 'delta',
+        mode: str = 'overwrite',
+        options: Optional[dict[str, str]] = None,
+        partition_by: Optional[list[str]] = None,
+) -> None:
+    """Saves a DataFrame to a catalog table or file path.
+
+    Args:
+        df: The PySpark DataFrame to save.
+        data_path: The destination path. If it contains no '/', saves as a catalog table; otherwise, as a file path.
+        data_format: The format to save in (e.g., 'delta', 'parquet'). Defaults to 'delta'.
+        mode: The save mode ('overwrite', 'append', 'ignore', 'error'). Defaults to 'overwrite'.
+        options: Optional dictionary of additional options for the writer.
+        partition_by: Optional list of column names to partition by.
+
+    Returns:
+        None
+
+    Raises:
+        ValueError: If the DataFrame or save mode is invalid.
+
+    Example:
+        >>> save_data(df, "db.events")
+        >>> save_data(df, "/data/events", data_format="parquet", mode="append")
+        >>> save_data(df, "db.events", partition_by=["year", "month"])
+    """
+    writer = df.write.format(data_format).mode(mode)
+
+    if options:
+        writer = writer.options(**options)
+
+    if partition_by:
+        writer = writer.partitionBy(*partition_by)
+
+    if _is_catalog_path(data_path):
+        writer.saveAsTable(data_path)
+    else:
+        writer.save(data_path)
+
+    print(f"Data saved successfully to '{data_path}' in '{data_format}' format with mode '{mode}'.")