sparkless-testing 0.2.0__tar.gz → 4.20.0__tar.gz

sparkless_testing-4.20.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: sparkless-testing
+Version: 4.20.0
+Summary: Backend-independent pytest helpers for Sparkless and PySpark test suites.
+License: MIT
+Project-URL: Homepage, https://github.com/eddiethedean/robin-sparkless
+Project-URL: Documentation, https://robin-sparkless.readthedocs.io/
+Project-URL: Repository, https://github.com/eddiethedean/robin-sparkless
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: pytest>=7
+
+# sparkless-testing
+
+Backend-independent pytest fixtures and helpers for test suites that run against
+Sparkless or PySpark. Install `sparkless[testing]` when testing a Sparkless
+application, or install `sparkless-testing` directly for a suite that selects its
+backend independently.
+
+```bash
+python -m pip install "sparkless[testing]==4.20.0"
+```
+
+Add this to your suite's root `conftest.py` to load the fixtures and backend
+markers:
+
+```python
+pytest_plugins = ["sparkless_testing.plugin"]
+```
+
+Use the `spark` fixture in your tests. It selects Sparkless by default. To
+run the same tests on a local PySpark installation, set `SPARKLESS_TEST_MODE=pyspark`.
+The [testing guide](https://robin-sparkless.readthedocs.io/en/latest/TESTING_GUIDE/)
+covers PySpark and Java setup and the compatibility profiles.
+
+Use `compare_dataframes()` for structured row, ordered-column, and schema
+results, or `assert_dataframes_equal()` to fail a test on any difference. Schema
+checks cover names/order, types, nullability, declared metadata, decimals, and
+nested struct/array/map fields. An expected mapping can declare `schema` and an
+empty `data` list. See the
+[comparison API contract](https://robin-sparkless.readthedocs.io/en/latest/TESTING_PYTHON_API/#comparison-semantics).
+
+The published 4.19.0 package had the schema comparison defect in
+[#1746](https://github.com/eddiethedean/robin-sparkless/issues/1746). Version
+4.20.0 fixes schema comparison for empty results and nested types.

sparkless_testing-4.20.0/README.md

@@ -0,0 +1,33 @@
+# sparkless-testing
+
+Backend-independent pytest fixtures and helpers for test suites that run against
+Sparkless or PySpark. Install `sparkless[testing]` when testing a Sparkless
+application, or install `sparkless-testing` directly for a suite that selects its
+backend independently.
+
+```bash
+python -m pip install "sparkless[testing]==4.20.0"
+```
+
+Add this to your suite's root `conftest.py` to load the fixtures and backend
+markers:
+
+```python
+pytest_plugins = ["sparkless_testing.plugin"]
+```
+
+Use the `spark` fixture in your tests. It selects Sparkless by default. To
+run the same tests on a local PySpark installation, set `SPARKLESS_TEST_MODE=pyspark`.
+The [testing guide](https://robin-sparkless.readthedocs.io/en/latest/TESTING_GUIDE/)
+covers PySpark and Java setup and the compatibility profiles.
+
+Use `compare_dataframes()` for structured row, ordered-column, and schema
+results, or `assert_dataframes_equal()` to fail a test on any difference. Schema
+checks cover names/order, types, nullability, declared metadata, decimals, and
+nested struct/array/map fields. An expected mapping can declare `schema` and an
+empty `data` list. See the
+[comparison API contract](https://robin-sparkless.readthedocs.io/en/latest/TESTING_PYTHON_API/#comparison-semantics).
+
+The published 4.19.0 package had the schema comparison defect in
+[#1746](https://github.com/eddiethedean/robin-sparkless/issues/1746). Version
+4.20.0 fixes schema comparison for empty results and nested types.

sparkless_testing-4.20.0/pyproject.toml

@@ -0,0 +1,23 @@
+[project]
+name = "sparkless-testing"
+version = "4.20.0"
+description = "Backend-independent pytest helpers for Sparkless and PySpark test suites."
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+dependencies = ["pytest>=7"]
+
+[project.urls]
+Homepage = "https://github.com/eddiethedean/robin-sparkless"
+Documentation = "https://robin-sparkless.readthedocs.io/"
+Repository = "https://github.com/eddiethedean/robin-sparkless"
+
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = ["sparkless_testing"]
+
+[tool.setuptools.package-data]
+sparkless_testing = ["py.typed"]

sparkless_testing-4.20.0/sparkless_testing/__init__.py

@@ -0,0 +1,120 @@
+"""Dual sparkless/pyspark testing framework.
+
+This module provides a unified API for writing tests that can run against
+both sparkless (Rust/Polars) and PySpark backends. Use the SPARKLESS_TEST_MODE
+environment variable to switch between modes:
+
+- SPARKLESS_TEST_MODE=sparkless (default): Run with sparkless
+- SPARKLESS_TEST_MODE=pyspark: Run with PySpark
+
+Quick Start (for external projects):
+
+1. Add to your conftest.py:
+
+    pytest_plugins = ["sparkless_testing.plugin"]
+
+2. Use the `spark` fixture in your tests:
+
+    def test_filter(spark):
+        df = spark.createDataFrame([(1, "a"), (2, "b")], ["id", "val"])
+        result = df.filter(df.id > 1).collect()
+        assert len(result) == 1
+
+3. Run tests:
+
+    # Run with sparkless (default)
+    pytest tests/
+
+    # Run with PySpark
+    SPARKLESS_TEST_MODE=pyspark pytest tests/
+
+For more control, use the module directly:
+
+    from sparkless_testing import Mode, create_session, get_imports
+
+    spark = create_session(mode=Mode.SPARKLESS)
+    imports = get_imports()
+    F = imports.F
+
+Example usage with comparison utilities:
+
+    from sparkless_testing import assert_dataframes_equal, assert_rows_equal
+
+    def test_transform(spark):
+        df1 = transform_a(spark)
+        df2 = transform_b(spark)
+        assert_dataframes_equal(df1, df2, check_order=False)
+"""
+
+from __future__ import annotations
+
+# Mode detection and configuration
+from .mode import (
+    Mode,
+    ENV_VAR_NAME,
+    get_mode,
+    is_pyspark_mode,
+    is_sparkless_mode,
+    set_mode,
+)
+
+from .compat import (
+    ENV_COMPAT,
+    DEFAULT_COMPAT,
+    get_compat_profile,
+    apply_compat_to_session,
+)
+
+# Session creation
+from .session import create_session
+
+# Unified imports
+from .imports import SparkImports, get_imports
+
+# Comparison utilities
+from .comparison import (
+    ComparisonResult,
+    compare_dataframes,
+    assert_dataframes_equal,
+    assert_rows_equal,
+)
+
+# Pytest fixtures (for direct import if not using plugin)
+from .fixtures import (
+    spark,
+    spark_mode,
+    spark_imports,
+    isolated_session,
+    table_prefix,
+)
+
+__all__ = [
+    # Mode
+    "Mode",
+    "ENV_VAR_NAME",
+    "get_mode",
+    "is_pyspark_mode",
+    "is_sparkless_mode",
+    "set_mode",
+    # Compat profile
+    "ENV_COMPAT",
+    "DEFAULT_COMPAT",
+    "get_compat_profile",
+    "apply_compat_to_session",
+    # Session
+    "create_session",
+    # Imports
+    "SparkImports",
+    "get_imports",
+    # Comparison
+    "ComparisonResult",
+    "compare_dataframes",
+    "assert_dataframes_equal",
+    "assert_rows_equal",
+    # Fixtures
+    "spark",
+    "spark_mode",
+    "spark_imports",
+    "isolated_session",
+    "table_prefix",
+]