sparkdq 0.1.0__tar.gz

sparkdq-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 Marcel Kennert
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

sparkdq-0.1.0/PKG-INFO

@@ -0,0 +1,162 @@
+Metadata-Version: 2.4
+Name: sparkdq
+Version: 0.1.0
+Summary: A declarative PySpark framework for row- and aggregate-level data quality validation.
+Author-email: Marcel Kennert <marcel.kennert@gmx.de>
+Project-URL: homepage, https://github.com/sparkdq-community/sparkdq
+Project-URL: documentation, https://sparkdq-community.github.io/sparkdq/
+Keywords: data-quality,data-validation,pyspark,spark,etl,data-pipeline,apache-spark,lightweight
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyspark<4.0.0,>=3.5.0
+Dynamic: license-file
+
+[![CI Pipeline](https://github.com/sparkdq-community/sparkdq/actions/workflows/ci.yaml/badge.svg)](https://github.com/sparkdq-community/sparkdq/actions/workflows/ci.yaml)
+[![codecov](https://codecov.io/gh/sparkdq-community/sparkdq/branch/main/graph/badge.svg?token=3TVZE8J2DN)](https://codecov.io/gh/sparkdq-community/sparkdq)
+[![Docs](https://img.shields.io/badge/docs-online-blue.svg)](https://sparkdq-community.github.io/sparkdq/)
+[![Python Versions](https://img.shields.io/badge/python-3.10%20|%203.11%20|%203.12-blue.svg)](https://github.com/sparkdq-community/sparkdq)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+
+# SparkDQ — Data Quality Validation for Apache Spark
+
+Most data quality frameworks weren’t designed with PySpark in mind. They aren’t Spark-native and often lack proper support for declarative pipelines. Instead of integrating seamlessly, they require you to build custom wrappers around them just to fit into production workflows. This adds complexity and makes your pipelines harder to maintain. On top of that, many frameworks only validate data after processing — so you can’t react dynamically or fail early when data issues occur.
+
+**SparkDQ** takes a different approach. It’s built specifically for PySpark — so you can define and run data quality checks directly inside your Spark pipelines, using Python. Whether you're validating incoming data, verifying outputs before persistence, or enforcing assumptions in your dataflow: SparkDQ helps you catch issues early, without adding complexity.
+
+🚀  See the [official documentation](https://sparkdq-community.github.io/sparkdq/) to learn more.
+
+## Quickstart Examples
+
+SparkDQ lets you define checks either using a **Python-native** interface or via **declarative configuration** (e.g. YAML, JSON, or database-driven). Regardless of how you define them, all checks are added to a `CheckSet` — which you pass to the validation engine. That’s it! Choose the style that fits your use case, and SparkDQ takes care of the rest.
+
+### Python-Native Approach
+
+```python
+from pyspark.sql import SparkSession
+
+from sparkdq.checks import NullCheckConfig
+from sparkdq.engine import BatchDQEngine
+from sparkdq.management import CheckSet
+
+spark = SparkSession.builder.getOrCreate()
+
+df = spark.createDataFrame([
+    {"id": 1, "name": "Alice"},
+    {"id": 2, "name": None},
+    {"id": 3, "name": "Bob"},
+])
+
+# Define checks using the Python-native interface (no external config needed)
+check_set = CheckSet()
+check_set.add_check(NullCheckConfig(check_id="my-null-check", columns=["name"]))
+
+result = BatchDQEngine(check_set).run_batch(df)
+print(result.summary())
+```
+
+### Declarative Approach
+
+```python
+from pyspark.sql import SparkSession
+
+from sparkdq.engine import BatchDQEngine
+from sparkdq.management import CheckSet
+
+spark = SparkSession.builder.getOrCreate()
+
+df = spark.createDataFrame(
+    [
+        {"id": 1, "name": "Alice"},
+        {"id": 2, "name": None},
+        {"id": 3, "name": "Bob"},
+    ]
+)
+
+# Declarative configuration via dictionary
+# Could be loaded from YAML, JSON, or any external system
+check_definitions = [
+    {"check-id": "my-null-check", "check": "null-check", "columns": ["name"]},
+]
+check_set = CheckSet()
+check_set.add_checks_from_dicts(check_definitions)
+
+result = BatchDQEngine(check_set).run_batch(df)
+print(result.summary())
+```
+
+SparkDQ is designed to integrate seamlessly into real-world systems. Instead of relying on a custom DSL or
+rigid schemas, it accepts plain Python dictionaries for check definitions. This makes it easy to load checks
+from YAML or JSON files, configuration tables in databases, or even remote APIs — enabling smooth integration
+into orchestration tools, CI pipelines, and data contract workflows.
+
+## Installation
+
+Install the latest stable version using pip:
+
+```
+pip install sparkdq
+```
+
+Alternatively, if you're using uv, a fast and modern Python package manager:
+
+```
+uv add sparkdq
+```
+
+The framework supports Python 3.10+ and is fully tested with PySpark 3.5.x. No additional Spark installation
+is required when running inside environments like Databricks, AWS Glue, or EMR.
+
+## Why SparkDQ?
+
+* ✅ **Robust Validation Layer**: Clean separation of check definition, execution, and reporting
+
+* ✅ **Declarative or Programmatic**: Define checks via config files or directly in Python
+
+* ✅ **Severity-Aware**: Built-in distinction between warning and critical violations
+
+* ✅ **Row & Aggregate Logic**: Supports both record-level and dataset-wide constraints
+
+* ✅ **Typed & Tested**: Built with type safety, testability, and extensibility in mind
+
+* ✅ **Zero Overhead**: Pure PySpark, no heavy dependencies
+
+## Typical Use Cases
+
+SparkDQ is built for modern data platforms that demand trust, transparency, and resilience.
+It helps teams enforce quality standards early and consistently — across ingestion, transformation, and delivery layers.
+
+Whether you're building a real-time ingestion pipeline or curating a data product for thousands of downstream users,
+SparkDQ lets you define and execute checks that are precise, scalable, and easy to maintain.
+
+Common Scenarios:
+
+* ✅ Validating raw ingestion data
+
+* ✅ Enforcing schema and content rules before persisting to a lakehouse (Delta, Iceberg, Hudi)
+
+* ✅ Asserting quality conditions before analytics or ML training jobs
+
+* ✅ Flagging critical violations in batch pipelines via structured summaries and alerts
+
+* ✅ Driving Data Contracts: Use declarative checks in CI pipelines to catch issues before deployment
+
+## Let’s Build Better Data Together
+
+⭐️ Found this useful? Give it a star and help spread the word!
+
+📣 Questions, feedback, or ideas? Open an issue or discussion — we’d love to hear from you.
+
+🤝 Want to contribute? Check out [CONTRIBUTING.md](https://github.com/sparkdq-community/sparkdq/blob/main/CONTRIBUTING.md) to get started.

sparkdq-0.1.0/README.md

@@ -0,0 +1,136 @@
+[![CI Pipeline](https://github.com/sparkdq-community/sparkdq/actions/workflows/ci.yaml/badge.svg)](https://github.com/sparkdq-community/sparkdq/actions/workflows/ci.yaml)
+[![codecov](https://codecov.io/gh/sparkdq-community/sparkdq/branch/main/graph/badge.svg?token=3TVZE8J2DN)](https://codecov.io/gh/sparkdq-community/sparkdq)
+[![Docs](https://img.shields.io/badge/docs-online-blue.svg)](https://sparkdq-community.github.io/sparkdq/)
+[![Python Versions](https://img.shields.io/badge/python-3.10%20|%203.11%20|%203.12-blue.svg)](https://github.com/sparkdq-community/sparkdq)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+
+# SparkDQ — Data Quality Validation for Apache Spark
+
+Most data quality frameworks weren’t designed with PySpark in mind. They aren’t Spark-native and often lack proper support for declarative pipelines. Instead of integrating seamlessly, they require you to build custom wrappers around them just to fit into production workflows. This adds complexity and makes your pipelines harder to maintain. On top of that, many frameworks only validate data after processing — so you can’t react dynamically or fail early when data issues occur.
+
+**SparkDQ** takes a different approach. It’s built specifically for PySpark — so you can define and run data quality checks directly inside your Spark pipelines, using Python. Whether you're validating incoming data, verifying outputs before persistence, or enforcing assumptions in your dataflow: SparkDQ helps you catch issues early, without adding complexity.
+
+🚀  See the [official documentation](https://sparkdq-community.github.io/sparkdq/) to learn more.
+
+## Quickstart Examples
+
+SparkDQ lets you define checks either using a **Python-native** interface or via **declarative configuration** (e.g. YAML, JSON, or database-driven). Regardless of how you define them, all checks are added to a `CheckSet` — which you pass to the validation engine. That’s it! Choose the style that fits your use case, and SparkDQ takes care of the rest.
+
+### Python-Native Approach
+
+```python
+from pyspark.sql import SparkSession
+
+from sparkdq.checks import NullCheckConfig
+from sparkdq.engine import BatchDQEngine
+from sparkdq.management import CheckSet
+
+spark = SparkSession.builder.getOrCreate()
+
+df = spark.createDataFrame([
+    {"id": 1, "name": "Alice"},
+    {"id": 2, "name": None},
+    {"id": 3, "name": "Bob"},
+])
+
+# Define checks using the Python-native interface (no external config needed)
+check_set = CheckSet()
+check_set.add_check(NullCheckConfig(check_id="my-null-check", columns=["name"]))
+
+result = BatchDQEngine(check_set).run_batch(df)
+print(result.summary())
+```
+
+### Declarative Approach
+
+```python
+from pyspark.sql import SparkSession
+
+from sparkdq.engine import BatchDQEngine
+from sparkdq.management import CheckSet
+
+spark = SparkSession.builder.getOrCreate()
+
+df = spark.createDataFrame(
+    [
+        {"id": 1, "name": "Alice"},
+        {"id": 2, "name": None},
+        {"id": 3, "name": "Bob"},
+    ]
+)
+
+# Declarative configuration via dictionary
+# Could be loaded from YAML, JSON, or any external system
+check_definitions = [
+    {"check-id": "my-null-check", "check": "null-check", "columns": ["name"]},
+]
+check_set = CheckSet()
+check_set.add_checks_from_dicts(check_definitions)
+
+result = BatchDQEngine(check_set).run_batch(df)
+print(result.summary())
+```
+
+SparkDQ is designed to integrate seamlessly into real-world systems. Instead of relying on a custom DSL or
+rigid schemas, it accepts plain Python dictionaries for check definitions. This makes it easy to load checks
+from YAML or JSON files, configuration tables in databases, or even remote APIs — enabling smooth integration
+into orchestration tools, CI pipelines, and data contract workflows.
+
+## Installation
+
+Install the latest stable version using pip:
+
+```
+pip install sparkdq
+```
+
+Alternatively, if you're using uv, a fast and modern Python package manager:
+
+```
+uv add sparkdq
+```
+
+The framework supports Python 3.10+ and is fully tested with PySpark 3.5.x. No additional Spark installation
+is required when running inside environments like Databricks, AWS Glue, or EMR.
+
+## Why SparkDQ?
+
+* ✅ **Robust Validation Layer**: Clean separation of check definition, execution, and reporting
+
+* ✅ **Declarative or Programmatic**: Define checks via config files or directly in Python
+
+* ✅ **Severity-Aware**: Built-in distinction between warning and critical violations
+
+* ✅ **Row & Aggregate Logic**: Supports both record-level and dataset-wide constraints
+
+* ✅ **Typed & Tested**: Built with type safety, testability, and extensibility in mind
+
+* ✅ **Zero Overhead**: Pure PySpark, no heavy dependencies
+
+## Typical Use Cases
+
+SparkDQ is built for modern data platforms that demand trust, transparency, and resilience.
+It helps teams enforce quality standards early and consistently — across ingestion, transformation, and delivery layers.
+
+Whether you're building a real-time ingestion pipeline or curating a data product for thousands of downstream users,
+SparkDQ lets you define and execute checks that are precise, scalable, and easy to maintain.
+
+Common Scenarios:
+
+* ✅ Validating raw ingestion data
+
+* ✅ Enforcing schema and content rules before persisting to a lakehouse (Delta, Iceberg, Hudi)
+
+* ✅ Asserting quality conditions before analytics or ML training jobs
+
+* ✅ Flagging critical violations in batch pipelines via structured summaries and alerts
+
+* ✅ Driving Data Contracts: Use declarative checks in CI pipelines to catch issues before deployment
+
+## Let’s Build Better Data Together
+
+⭐️ Found this useful? Give it a star and help spread the word!
+
+📣 Questions, feedback, or ideas? Open an issue or discussion — we’d love to hear from you.
+
+🤝 Want to contribute? Check out [CONTRIBUTING.md](https://github.com/sparkdq-community/sparkdq/blob/main/CONTRIBUTING.md) to get started.

sparkdq-0.1.0/pyproject.toml

@@ -0,0 +1,128 @@
+[project]
+name = "sparkdq"
+version = "0.1.0"
+description = "A declarative PySpark framework for row- and aggregate-level data quality validation."
+authors = [{ name = "Marcel Kennert", email = "marcel.kennert@gmx.de" }]
+readme = "README.md"
+keywords = [
+  "data-quality",
+  "data-validation",
+  "pyspark",
+  "spark",
+  "etl",
+  "data-pipeline",
+  "apache-spark",
+  "lightweight"
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Information Technology",
+  "Intended Audience :: Science/Research",
+  "Topic :: Software Development :: Libraries",
+  "Topic :: Software Development :: Quality Assurance",
+  "Topic :: Scientific/Engineering :: Information Analysis",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Operating System :: OS Independent"
+]
+requires-python = ">=3.10"
+dependencies = [
+    "pyspark>=3.5.0,<4.0.0",
+]
+
+[project.urls]
+homepage = "https://github.com/sparkdq-community/sparkdq"
+documentation = "https://sparkdq-community.github.io/sparkdq/"
+
+[tool.uv]
+default-groups = "all"
+
+[dependency-groups]
+dev = [
+    "pre-commit>=4.2.0,<5.0.0"
+]
+lint = [
+    "ruff>=0.11.0,<1.0.0",
+    "mypy>=1.15.0,<2.0.0"
+]
+test = [
+    "pytest>=8.3.5,<9.0.0",
+    "pytest-cov>=6.1.0,<7.0.0",
+    "pyarrow>=19.0.0,<20.0.0",
+    "numpy<2.0.0",
+    "pandas>=2.0.0"
+]
+docs = [
+    "sphinx>=7.2.0,<8.0.0",
+    "sphinx-copybutton>=0.5.2,<1.0.0",
+    "sphinx-book-theme>=1.1.0,<2.0.0",
+    "myst-parser>=2.0.0,<3.0.0"
+]
+jupyter = [
+    "notebook>=7.3.3,<8.0.0",
+    "ipykernel>=6.20.0,<7.0.0"
+]
+
+[tool.mypy]
+python_version = "3.11"
+exclude = ["docs", "tests", "examples"]
+strict = true
+show_error_codes = true
+
+[tool.ruff]
+exclude = [
+    ".mypy_cache",
+    ".pytest_cache",
+    ".ruff_cache",
+    ".venv",
+    "docs",
+]
+line-length = 110
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "W"]
+extend-ignore = ["N812", "N803"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+filterwarnings = [
+  "ignore:.*distutils Version classes are deprecated.*:DeprecationWarning",
+  "ignore:.*PYARROW_IGNORE_TIMEZONE.*:UserWarning",
+]
+
+[tool.coverage.run]
+source = ["sparkdq"]
+
+[tool.semantic_release]
+commit_message = "chore(release): {version} [skip ci]\n\nAutomatically generated by python-semantic-release"
+commit_parser = "conventional"
+major_on_zero = false
+allow_zero_version = true
+version_toml = ["pyproject.toml:project.version"]
+version_variable = ["sparkdq/__init__.py:__version__"]
+
+[tool.semantic_release.changelog]
+exclude_commit_patterns = ["Merge branch*", "chore(release)*"]
+
+[tool.semantic_release.commit_parser_options]
+allowed_tags = [
+    "build",
+    "chore",
+    "ci",
+    "docs",
+    "feat",
+    "fix",
+    "perf",
+    "style",
+    "refactor",
+    "test",
+]
+minor_tags = ["feat"]
+patch_tags = ["fix", "perf", "refactor"]
+
+[tool.semantic_release.branches.main]
+match = "main"

sparkdq-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sparkdq-0.1.0/sparkdq/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

sparkdq-0.1.0/sparkdq/checks/__init__.py

@@ -0,0 +1,33 @@
+from .aggregate.count_checks.count_between_check import RowCountBetweenCheckConfig
+from .aggregate.count_checks.count_exact_check import RowCountExactCheckConfig
+from .aggregate.count_checks.count_max_check import RowCountMaxCheckConfig
+from .aggregate.count_checks.count_min_check import RowCountMinCheckConfig
+from .row_level.date_checks.date_between_check import DateBetweenCheckConfig
+from .row_level.date_checks.date_max_check import DateMaxCheckConfig
+from .row_level.date_checks.date_min_check import DateMinCheckConfig
+from .row_level.null_checks.not_null_check import NotNullCheckConfig
+from .row_level.null_checks.null_check import NullCheckConfig
+from .row_level.numeric_checks.numeric_between_check import NumericBetweenCheckConfig
+from .row_level.numeric_checks.numeric_max_check import NumericMaxCheckConfig
+from .row_level.numeric_checks.numeric_min_check import NumericMinCheckConfig
+from .row_level.timestamp_checks.timestamp_between_check import TimestampBetweenCheck
+from .row_level.timestamp_checks.timestamp_max_check import TimestampMaxCheckConfig
+from .row_level.timestamp_checks.timestamp_min_check import TimestampMinCheckConfig
+
+__all__ = [
+    "NullCheckConfig",
+    "NotNullCheckConfig",
+    "RowCountMinCheckConfig",
+    "RowCountMaxCheckConfig",
+    "RowCountExactCheckConfig",
+    "RowCountBetweenCheckConfig",
+    "NumericMinCheckConfig",
+    "NumericMaxCheckConfig",
+    "NumericBetweenCheckConfig",
+    "DateMinCheckConfig",
+    "DateMaxCheckConfig",
+    "DateBetweenCheckConfig",
+    "TimestampMinCheckConfig",
+    "TimestampMaxCheckConfig",
+    "TimestampBetweenCheck",
+]