e6data-spark-compatibility 1.0.0__tar.gz

e6data_spark_compatibility-1.0.0/LICENSE

@@ -0,0 +1,69 @@
+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
+
+Copyright 2024 E6Data
+
+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.

e6data_spark_compatibility-1.0.0/PKG-INFO

@@ -0,0 +1,424 @@
+Metadata-Version: 2.4
+Name: e6data-spark-compatibility
+Version: 1.0.0
+Summary: PySpark and Sedona compatibility layer for e6data
+Home-page: https://github.com/e6data/e6-spark-compat
+Author: E6Data
+Author-email: support@e6data.com
+Project-URL: Bug Reports, https://github.com/e6data/e6-spark-compat/issues
+Project-URL: Source, https://github.com/e6data/e6-spark-compat
+Project-URL: Documentation, https://github.com/e6data/e6-spark-compat/blob/main/README.md
+Keywords: pyspark spark sql dataframe e6data compatibility sedona spatial
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: Topic :: Database
+Classifier: Topic :: Database :: Database Engines/Servers
+Classifier: Topic :: Scientific/Engineering :: GIS
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+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: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: e6data-python-connector>=2.3.10
+Requires-Dist: pandas>=1.0.0
+Requires-Dist: numpy>=1.18.0
+Provides-Extra: dev
+Requires-Dist: pytest>=6.0; extra == "dev"
+Requires-Dist: pytest-cov>=2.0; extra == "dev"
+Requires-Dist: pytest-html>=3.0; extra == "dev"
+Requires-Dist: black>=22.0; extra == "dev"
+Requires-Dist: flake8>=3.8; extra == "dev"
+Requires-Dist: mypy>=0.910; extra == "dev"
+Provides-Extra: spatial
+Requires-Dist: geopandas>=0.10.0; extra == "spatial"
+Requires-Dist: shapely>=1.8.0; extra == "spatial"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# e6-spark-compat
+
+A PySpark and Sedona compatibility layer for e6data, providing seamless migration from PySpark to e6data with minimal code changes.
+
+## Overview
+
+e6-spark-compat is a production-ready compatibility library that translates PySpark and Apache Sedona operations into optimized e6data SQL queries. The library implements lazy evaluation, professional SQL generation using SQLGlot, and comprehensive PySpark API compatibility.
+
+### Key Features
+
+- **Lazy Evaluation**: Build query plans that execute only when actions are called
+- **Professional SQL Generation**: SQLGlot-based AST optimization for high-performance queries
+- **Complete PySpark API**: DataFrame operations, SQL functions, window functions, and aggregations
+- **Spatial Operations**: Full Apache Sedona compatibility with ST_* functions
+- **Window Functions**: Complete Window specification API for advanced analytics
+- **Multiple File Formats**: Parquet, ORC, CSV, JSON, and GeoParquet support
+- **Dual-Mode Test Suite**: 1270 tests run offline (SQL validation) and live (cluster execution)
+- **CI/CD**: GitHub Actions with offline (automatic) and live (manual) test runs
+
+## Installation
+
+### For Users
+
+```bash
+# Install from PyPI
+pip install e6data-spark-compatibility
+
+# Install from GitHub
+pip install git+https://github.com/e6data/e6-spark-compat.git
+
+# Install from local clone
+git clone https://github.com/e6data/e6-spark-compat.git
+cd e6-spark-compat
+pip install -e .
+```
+
+### For Developers
+
+```bash
+# Clone the repository
+git clone https://github.com/e6data/e6-spark-compat.git
+cd e6-spark-compat
+
+# Install with development dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest tests/
+```
+
+## Quick Start
+
+### Migration from PySpark
+
+Simply change your import statements - everything else stays the same:
+
+```python
+# Before: PySpark imports
+# from pyspark.sql import SparkSession
+# from pyspark.sql.functions import col, upper, count, sum, row_number
+# from pyspark.sql.window import Window
+
+# After: e6-spark-compat imports
+from e6_spark_compat import SparkSession
+from e6_spark_compat.sql.functions import col, upper, count, sum, row_number
+from e6_spark_compat.sql.window import Window
+
+# Connection configuration
+spark = (SparkSession.builder
+    .appName("E6DataExample")
+    .config("spark.e6data.host", "your-host")
+    .config("spark.e6data.username", "your-username")
+    .config("spark.e6data.password", "your-password")
+    .config("spark.e6data.database", "your-database")
+    .config("spark.e6data.catalog", "your-catalog")
+    .config("spark.e6data.cluster", "your-cluster-name")
+    .config("spark.e6data.secure", True)
+    .getOrCreate())
+
+# All PySpark operations work identically
+df = spark.read.parquet("s3://bucket/path/to/data.parquet")
+
+# Transformations (lazy evaluation)
+result = (df.filter(col("age") > 21)
+    .select("name", upper(col("city")).alias("city_upper"), "salary")
+    .groupBy("city_upper")
+    .agg(
+        count("*").alias("total_people"),
+        sum("salary").alias("total_salary")
+    )
+    .orderBy(col("total_people").desc()))
+
+# Action triggers execution
+result.show()
+```
+
+### Window Functions
+
+```python
+from e6_spark_compat.sql.window import Window
+from e6_spark_compat.sql.functions import row_number, rank, lag
+
+# Window specifications
+window_spec = Window.partitionBy("department").orderBy("salary")
+frame_spec = (Window.partitionBy("team").orderBy("hire_date")
+    .rowsBetween(Window.UNBOUNDED_PRECEDING, Window.CURRENT_ROW))
+
+# Window functions
+df_with_analytics = df.select(
+    "*",
+    row_number().over(window_spec).alias("rank"),
+    lag("salary", 1).over(window_spec).alias("prev_salary"),
+    sum("salary").over(frame_spec).alias("running_total")
+)
+```
+
+## Spatial Support
+
+For spatial operations with Sedona compatibility:
+
+```python
+from e6_spark_compat.sedona import SedonaRegistrator
+from e6_spark_compat.sql.functions import expr
+
+# Register Sedona functions
+SedonaRegistrator.registerAll(spark)
+
+# Use spatial functions
+points_df = spark.read.parquet("s3://bucket/points.parquet")
+polygons_df = spark.read.parquet("s3://bucket/polygons.parquet")
+
+# Spatial join
+result = points_df.join(
+    polygons_df,
+    expr("ST_Contains(polygons_df.geometry, ST_Point(points_df.lon, points_df.lat))"),
+    "inner"
+)
+```
+
+## Comprehensive Feature Set
+
+### DataFrame Operations
+- **Transformations**: `select()`, `filter()`/`where()`, `join()`, `groupBy()`, `orderBy()`/`sort()`, `limit()`, `distinct()`
+- **Set Operations**: `union()`, `intersect()`, `exceptAll()`
+- **Column Operations**: `withColumn()`, `withColumnRenamed()`, `drop()`, `cast()`
+- **Caching**: `cache()`/`persist()`, `unpersist()`
+
+### Action Methods
+- **Data Retrieval**: `collect()`, `count()`, `first()`, `take()`, `head()`
+- **Display**: `show()`, `explain()`, `describe()`
+- **Export**: `toPandas()`, `write.parquet()`, `write.orc()`, `write.csv()`, `write.json()`
+- **Views**: `createOrReplaceTempView()`, `createGlobalTempView()`
+
+### SQL Functions (135+)
+- **String Functions**: `upper`, `lower`, `concat`, `substring`, `trim`, `split`, `regexp_replace`, `length`
+- **Math Functions**: `abs`, `round`, `floor`, `ceil`, `sqrt`, `pow`, `sin`, `cos`, `log`
+- **Aggregate Functions**: `sum`, `avg`, `count`, `min`, `max`, `first`, `last`, `collect_list`
+- **Date/Time Functions**: `year`, `month`, `dayofmonth`, `hour`, `minute`, `date_add`, `date_sub`, `datediff`
+- **Window Functions**: `row_number`, `rank`, `dense_rank`, `percent_rank`, `ntile`, `lag`, `lead`
+- **Conditional Functions**: `when`, `coalesce`, `isnull`, `isnan`, `greatest`, `least`
+- **Hash Functions**: `md5`, `sha1`, `sha2`, `hash`, `xxhash64`
+- **Array Functions**: `array`, `array_contains`, `explode`, `size`, `array_sort`, and 16 more
+- **Map Functions**: `map_keys`, `map_values`, `map_from_arrays`, `map_concat`
+- **JSON Functions**: `get_json_object`, `json_extract`, `from_json`, `to_json`
+
+### Spatial Operations (Sedona Compatible)
+- **Geometry Functions**: All ST_* functions including `ST_Point`, `ST_Polygon`, `ST_Buffer`
+- **Spatial Relationships**: `ST_Contains`, `ST_Intersects`, `ST_Distance`, `ST_Within`
+- **Transformations**: `ST_Transform`, `ST_Centroid`, `ST_ConvexHull`
+- **Indexing**: H3 and GeoHash spatial indexing support
+
+## Testing
+
+### Test Suite Overview
+
+The test suite uses **dual-mode execution**: tests run offline by default (mock connection, SQL validation) and can also execute on a live e6data cluster when credentials are provided.
+
+| Category | Tests | Description |
+|---|---|---|
+| E2E SQL Generation | 360 | Full pipeline: PySpark API → SQL string validation |
+| TPC-DS Translations | 37 | Standard benchmark queries (37 of 99 TPC-DS queries) |
+| TPC-DS Analytics | 22 | Complex analytics workloads (star schema, RFM, ETL pipelines) |
+| SQLGlot Expressions | 288 | SQL expression generation via SQLGlot |
+| Integration | 227 | Query plan node composition |
+| Unit | 200 | Individual class/method tests |
+| Writer | 38 | DataFrameWriter operations |
+| Workloads | 94 | Customer workload pipeline tests (Kroger DQ + DFM analytics) |
+| **Total** | **1270** | **1263 pass, 7 known failures** |
+
+### Customer Scripts
+
+Standalone scripts that exercise real customer pipelines end-to-end:
+
+| Script | Description | Dataset |
+|---|---|---|
+| `kroger_original_test.py` | Kroger pre-DQ validation pipeline | mars_full |
+| `e6_dfm_on_mars_full.py` | DFM pipeline patterns (39 tests) | mars_full |
+| `e6_dfm_test.py` | DFM feature coverage (42 tests) | TPC-DS |
+| `*_rust.py` variants | Same scripts with FORMAT_NUMBER workaround for rust engine |
+
+```bash
+# Run customer script on Java engine
+E6DATA_HOST=... S3_READ_BASE=... python tests/customer_scripts/kroger_original_test.py
+
+# Run on rust engine
+E6DATA_HOST=... S3_READ_BASE=... python tests/customer_scripts/kroger_original_test_rust.py
+```
+
+### Running Tests
+
+```bash
+# Offline (default) — fast, no cluster needed (~5 seconds)
+./run_tests.sh
+
+# Specific file or directory
+./run_tests.sh offline 1 tests/workloads/
+./run_tests.sh offline 1 tests/workloads/test_dfm_pipeline.py
+./run_tests.sh offline 1 tests/workloads/test_dfm_pipeline.py::TestDFMMissingFunctions
+
+# By keyword or marker
+./run_tests.sh offline 1 -k "dfm"
+./run_tests.sh offline 1 -m e2e
+
+# Or use pytest directly
+pytest tests/e2e/                    # E2E tests
+pytest tests/tpcds/                  # TPC-DS queries
+pytest tests/e2e/ -m spatial         # Spatial tests
+```
+
+### Live Mode (cluster execution)
+
+Set environment variables to run the same tests against a real e6data cluster:
+
+```bash
+export E6DATA_HOST="your-cluster-host"
+export E6DATA_PORT="443"
+export E6DATA_USERNAME="your-user"
+export E6DATA_PASSWORD="your-token"
+export E6DATA_DATABASE="tpcds_1000_delta"
+export E6DATA_CATALOG="your-catalog"
+export E6DATA_CLUSTER="your-cluster"
+
+# Sequential with full HTML report
+./run_tests.sh live
+
+# Parallel with N workers
+./run_tests.sh live 4
+./run_tests.sh live 8
+```
+
+In live mode, each test generates SQL (same as offline) **and** executes it on the cluster with `LIMIT 5`. The HTML report captures query IDs, row counts, execution times, and error details.
+
+### Test Reports
+
+Reports are auto-generated on every run:
+
+- **HTML**: `reports/test_report.html` — browsable report with expandable details per test:
+  - PySpark input source code
+  - Generated SQL
+  - Query ID (live mode)
+  - Engine error details (live mode, failures only)
+- **JUnit XML**: `reports/test_results.xml` — for CI/CD integration
+
+### CI / GitHub Actions
+
+Offline tests run automatically on every push/PR — no setup needed.
+
+Live tests are triggered manually (requires GitHub secrets configured):
+
+**From GitHub UI:**
+1. Go to **Actions** tab → **e6-spark-compat CI**
+2. Click **Run workflow**
+3. Select branch, cluster (`general` / `rust-azure-benchmark`), and worker count
+4. Click **Run workflow**
+
+**From CLI:**
+```bash
+gh workflow run tests.yml --ref main -f run_live=true -f cluster=general -f concurrency=4
+```
+
+The CI summary includes category breakdown tables, failure details, and the `dorny/test-reporter` renders an interactive test results tab.
+
+## Architecture
+
+### Core Components
+
+1. **Query Plan Tree**: AST-like nodes representing SQL operations (Filter, Project, Join, Aggregate, etc.)
+2. **SQLGlot Integration**: Professional SQL generation using AST-based optimization
+3. **Lazy Evaluation**: Operations build query plans without immediate execution
+4. **Connection Management**: Efficient e6data connection handling and query execution
+
+### Execution Flow
+
+1. **Build Phase**: DataFrame operations create query plan nodes
+2. **Optimization Phase**: SQLGlot optimizes the query plan using AST transformations
+3. **Generation Phase**: Query plans generate optimized SQL via SQLGlot
+4. **Execution Phase**: Actions trigger SQL execution on e6data
+5. **Result Phase**: Results returned in PySpark-compatible format
+
+## Development
+
+### Project Structure
+
+```
+e6_spark_compat/
+├── core/           # Session, connection, query plan, SQL generator
+├── sql/            # DataFrame, Column, functions, window, reader, writer, types
+├── spatial/        # Sedona-compatible ST_* functions
+└── sedona/         # SedonaRegistrator compatibility shim
+
+tests/
+├── e2e/              # E2E SQL generation tests (dual-mode: offline + live)
+├── tpcds/            # TPC-DS benchmark query translations (37 queries)
+├── integration/      # Query plan composition tests
+├── sqlglot_tests/    # SQLGlot expression tests
+├── unit/             # Unit tests
+├── workloads/        # Customer workload pipeline tests
+├── customer_scripts/ # Standalone customer pipeline scripts
+└── live/             # Live cluster-only execution tests
+```
+
+### Code Quality
+
+```bash
+# Format code
+black e6_spark_compat/
+
+# Run linting
+flake8 e6_spark_compat/
+
+# Type checking
+mypy e6_spark_compat/
+```
+
+## Migration Guide
+
+### From PySpark
+
+1. **Update Imports**: Change `pyspark` imports to `e6_spark_compat`
+2. **Configuration**: Update SparkSession configuration for e6data connection
+3. **Test**: Run your existing PySpark code - it should work unchanged
+
+### From Sedona
+
+1. **Spatial Functions**: Replace Sedona imports with `e6_spark_compat.spatial.functions`
+2. **Registration**: Use `SedonaRegistrator.registerAll(spark)` for compatibility
+3. **Geometry Types**: Spatial operations work identically to Sedona
+
+## Contributing
+
+We welcome contributions! Here's how to get started:
+
+1. Fork the repository
+2. Create a feature branch
+3. Add tests for new functionality
+4. Ensure all tests pass (`pytest tests/`)
+5. Submit a pull request
+
+## Support
+
+- **Documentation**: See `docs/pyspark-compatibility/` for detailed guides
+- **Issues**: Report bugs and feature requests on GitHub
+- **Contact**: support@e6data.com for enterprise support
+
+## License
+
+Apache License 2.0 - see [LICENSE](LICENSE) for details.