databricks-switch-plugin 1.0.0__tar.gz

databricks_switch_plugin-1.0.0/.gitignore

@@ -0,0 +1,173 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+# Databricks
+.databricks/
+
+# Project specific
+.clinerules/
+.vscode/
+scratch/**
+!scratch/README.md
+test_output/
+databricks.yml

databricks_switch_plugin-1.0.0/LICENSE

@@ -0,0 +1,69 @@
+                               Databricks License
+                        Copyright (2024) Databricks, Inc.
+
+    Definitions. 
+    
+    Agreement: The agreement between Databricks, Inc., and you governing 
+    the use of the Databricks Services, as that term is defined in 
+    the Master Cloud Services Agreement (MCSA) located at 
+    www.databricks.com/legal/mcsa.
+        
+    Licensed Materials: The source code, object code, data, and/or other 
+    works to which this license applies. 
+
+    Scope of Use. You may not use the Licensed Materials except in 
+    connection with your use of the Databricks Services pursuant to 
+    the Agreement. Your use of the Licensed Materials must comply at all 
+    times with any restrictions applicable to the Databricks Services, 
+    generally, and must be used in accordance with any applicable 
+    documentation. You may view, use, copy, modify, publish, and/or 
+    distribute the Licensed Materials solely for the purposes of using 
+    the Licensed Materials within or connecting to the Databricks Services.
+    If you do not agree to these terms, you may not view, use, copy, 
+    modify, publish, and/or distribute the Licensed Materials.
+    
+    Redistribution. You may redistribute and sublicense the Licensed 
+    Materials so long as all use is in compliance with these terms. 
+    In addition:
+        
+        -   You must give any other recipients a copy of this License;
+        -   You must cause any modified files to carry prominent notices 
+            stating that you changed the files; 
+        -   You must retain, in any derivative works that you distribute, 
+            all copyright, patent, trademark, and attribution notices, 
+            excluding those notices that do not pertain to any part of 
+            the derivative works; and
+        -   If a "NOTICE" text file is provided 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. 
+
+    You may add your own copyright statement to your modifications and may 
+    provide additional 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 Licensed Materials otherwise complies with the conditions stated 
+    in this License.
+
+    Termination. This license terminates automatically upon your breach of 
+    these terms or upon the termination of your Agreement. Additionally, 
+    Databricks may terminate this license at any time on notice. Upon 
+    termination, you must permanently delete the Licensed Materials and 
+    all copies thereof.
+
+    DISCLAIMER; LIMITATION OF LIABILITY. 
+
+    THE LICENSED MATERIALS ARE PROVIDED “AS-IS” AND WITH ALL FAULTS. 
+    DATABRICKS, ON BEHALF OF ITSELF AND ITS LICENSORS, SPECIFICALLY 
+    DISCLAIMS ALL WARRANTIES RELATING TO THE LICENSED MATERIALS, EXPRESS 
+    AND IMPLIED, INCLUDING, WITHOUT LIMITATION, IMPLIED WARRANTIES, 
+    CONDITIONS AND OTHER TERMS OF MERCHANTABILITY, SATISFACTORY QUALITY OR 
+    FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. DATABRICKS AND 
+    ITS LICENSORS TOTAL AGGREGATE LIABILITY RELATING TO OR ARISING OUT OF 
+    YOUR USE OF OR DATABRICKS’ PROVISIONING OF THE LICENSED MATERIALS SHALL 
+    BE LIMITED TO ONE THOUSAND ($1,000) DOLLARS.  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 LICENSED MATERIALS OR 
+    THE USE OR OTHER DEALINGS IN THE LICENSED MATERIALS.

databricks_switch_plugin-1.0.0/NOTICE

@@ -0,0 +1,6 @@
+[Project Name]
+
+Copyright (2018) Databricks, Inc.
+
+
+This Software includes software developed at Databricks (https://www.databricks.com/) and its use is subject to the included LICENSE file.

databricks_switch_plugin-1.0.0/PKG-INFO

@@ -0,0 +1,117 @@
+Metadata-Version: 2.4
+Name: databricks-switch-plugin
+Version: 1.0.0
+Summary: LLM-powered tool to convert SQL, code, and workflow files into Databricks notebooks.
+Project-URL: Documentation, https://databrickslabs.github.io/lakebridge
+Project-URL: Issues, https://github.com/databrickslabs/lakebridge/issues
+Project-URL: Source, https://github.com/databrickslabs/lakebridge
+Maintainer-email: Databricks Labs <labs-oss@databricks.com>
+License-File: LICENSE
+License-File: NOTICE
+Keywords: Conversion,Databricks,LLM,Migration,SQL
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Framework :: Pytest
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: Other/Proprietary License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Requires-Dist: anytree==2.13.0
+Requires-Dist: chardet==5.2.0
+Requires-Dist: httpx==0.28.1
+Requires-Dist: omegaconf==2.3.0
+Requires-Dist: pyyaml==6.0.2
+Requires-Dist: tenacity==9.1.2
+Requires-Dist: tiktoken==0.9.0
+Provides-Extra: dev
+Requires-Dist: black~=25.1.0; extra == 'dev'
+Requires-Dist: coverage[toml]~=7.8.0; extra == 'dev'
+Requires-Dist: databricks-connect~=17.0.1; extra == 'dev'
+Requires-Dist: databricks-labs-pylint~=0.4.0; extra == 'dev'
+Requires-Dist: databricks-labs-pytester>=0.3.0; extra == 'dev'
+Requires-Dist: databricks-sdk~=0.51.0; extra == 'dev'
+Requires-Dist: hatch; extra == 'dev'
+Requires-Dist: mypy~=1.10.0; extra == 'dev'
+Requires-Dist: pylint-pytest==2.0.0a0; extra == 'dev'
+Requires-Dist: pylint~=3.2.2; extra == 'dev'
+Requires-Dist: pytest-asyncio~=0.26.0; extra == 'dev'
+Requires-Dist: pytest-cov<6.0.0,>=5.0.0; extra == 'dev'
+Requires-Dist: pytest-xdist~=3.5.0; extra == 'dev'
+Requires-Dist: pytest~=8.3.5; extra == 'dev'
+Requires-Dist: python-dotenv>=1.0.0; extra == 'dev'
+Requires-Dist: ruff~=0.11.6; extra == 'dev'
+Requires-Dist: types-pytz~=2025.2; extra == 'dev'
+Requires-Dist: types-pyyaml~=6.0.12; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Switch
+LLM-Powered Code Conversion Plugin for Lakebridge
+
+## Project Description
+Switch is a Lakebridge transpiler plugin that transforms SQL and other source formats into Databricks-compatible notebooks using Large Language Models (LLMs). As a core component of the Lakebridge migration platform, Switch provides automated code conversion capabilities through a multi-stage processing pipeline designed for large-scale platform migrations.
+
+## Project Support
+Please note that all projects in the /databrickslabs github account are provided for your exploration only, and are not formally supported by Databricks with Service Level Agreements (SLAs).  They are provided AS-IS and we do not make any guarantees of any kind.  Please do not submit a support ticket relating to any issues arising from the use of these projects.
+
+Any issues discovered through the use of this project should be filed as GitHub Issues on the Repo.  They will be reviewed as time permits, but there are no formal SLAs for support.
+
+## Key Features
+- **AI-Powered Conversion**: Leverages Large Language Models for intelligent code transformation
+- **Multi-Format Support**: Converts various source formats including SQL, code files, and workflow definitions
+- **Flexible Output**: Generates multiple output formats tailored to your migration needs
+- **Built-in Templates**: Comprehensive conversion templates for common database and platform migrations
+- **Cloud-Native Processing**: Scalable execution on Databricks platform infrastructure
+- **Stateful Tracking**: Maintains conversion progress and results for large-scale migrations
+- **Extensible Design**: Customizable template system for specialized conversion requirements
+
+## Using the Project
+
+### Primary Usage: Lakebridge Integration
+Switch is primarily designed as a Lakebridge transpiler plugin. To use Switch for code conversion:
+
+1. **Install Lakebridge**: Follow the [Lakebridge documentation](https://databrickslabs.github.io/lakebridge)
+2. **Install Switch transpiler**: Use Lakebridge to install the Switch transpiler plugin
+3. **Run conversion**: Use Lakebridge's transpile command with Switch
+
+For complete usage instructions and configuration options, refer to the [Lakebridge documentation](https://databrickslabs.github.io/lakebridge).
+
+### Alternative Usage: Direct Deployment
+For advanced testing or direct control, you can deploy Switch directly to a Databricks workspace:
+
+**Cell 1: Install Switch package**
+
+From PyPI (stable):
+```python
+%pip install databricks-switch-plugin
+```
+
+Or from Test PyPI (development/preview versions):
+```python
+%pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple databricks-switch-plugin
+```
+
+**Cell 2: Deploy Switch to workspace**
+```python
+from databricks.sdk import WorkspaceClient
+from switch.api.installer import SwitchInstaller
+
+ws = WorkspaceClient()
+installer = SwitchInstaller(ws)
+result = installer.install()
+
+print(f"Switch job created: {result.job_url}")
+```
+
+After installation, use the created job in Databricks Jobs UI to run conversions with your specific parameters.
+
+## For Developers
+For development setup, advanced usage, testing, and technical details, see [DEVELOPER.md](./DEVELOPER.md).

databricks_switch_plugin-1.0.0/README.md

@@ -0,0 +1,62 @@
+# Switch
+LLM-Powered Code Conversion Plugin for Lakebridge
+
+## Project Description
+Switch is a Lakebridge transpiler plugin that transforms SQL and other source formats into Databricks-compatible notebooks using Large Language Models (LLMs). As a core component of the Lakebridge migration platform, Switch provides automated code conversion capabilities through a multi-stage processing pipeline designed for large-scale platform migrations.
+
+## Project Support
+Please note that all projects in the /databrickslabs github account are provided for your exploration only, and are not formally supported by Databricks with Service Level Agreements (SLAs).  They are provided AS-IS and we do not make any guarantees of any kind.  Please do not submit a support ticket relating to any issues arising from the use of these projects.
+
+Any issues discovered through the use of this project should be filed as GitHub Issues on the Repo.  They will be reviewed as time permits, but there are no formal SLAs for support.
+
+## Key Features
+- **AI-Powered Conversion**: Leverages Large Language Models for intelligent code transformation
+- **Multi-Format Support**: Converts various source formats including SQL, code files, and workflow definitions
+- **Flexible Output**: Generates multiple output formats tailored to your migration needs
+- **Built-in Templates**: Comprehensive conversion templates for common database and platform migrations
+- **Cloud-Native Processing**: Scalable execution on Databricks platform infrastructure
+- **Stateful Tracking**: Maintains conversion progress and results for large-scale migrations
+- **Extensible Design**: Customizable template system for specialized conversion requirements
+
+## Using the Project
+
+### Primary Usage: Lakebridge Integration
+Switch is primarily designed as a Lakebridge transpiler plugin. To use Switch for code conversion:
+
+1. **Install Lakebridge**: Follow the [Lakebridge documentation](https://databrickslabs.github.io/lakebridge)
+2. **Install Switch transpiler**: Use Lakebridge to install the Switch transpiler plugin
+3. **Run conversion**: Use Lakebridge's transpile command with Switch
+
+For complete usage instructions and configuration options, refer to the [Lakebridge documentation](https://databrickslabs.github.io/lakebridge).
+
+### Alternative Usage: Direct Deployment
+For advanced testing or direct control, you can deploy Switch directly to a Databricks workspace:
+
+**Cell 1: Install Switch package**
+
+From PyPI (stable):
+```python
+%pip install databricks-switch-plugin
+```
+
+Or from Test PyPI (development/preview versions):
+```python
+%pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple databricks-switch-plugin
+```
+
+**Cell 2: Deploy Switch to workspace**
+```python
+from databricks.sdk import WorkspaceClient
+from switch.api.installer import SwitchInstaller
+
+ws = WorkspaceClient()
+installer = SwitchInstaller(ws)
+result = installer.install()
+
+print(f"Switch job created: {result.job_url}")
+```
+
+After installation, use the created job in Databricks Jobs UI to run conversions with your specific parameters.
+
+## For Developers
+For development setup, advanced usage, testing, and technical details, see [DEVELOPER.md](./DEVELOPER.md).

databricks_switch_plugin-1.0.0/lsp/config.yml

@@ -0,0 +1,99 @@
+# Switch transpiler configuration for Lakebridge integration
+# This file enables Lakebridge to discover and use Switch as a transpiler
+remorph:
+  version: 1
+  name: switch
+  command_line: ["echo", "Switch uses Jobs API, not LSP"]
+  dialects:
+    # SQL dialects
+    - mysql
+    - netezza  
+    - oracle
+    - postgresql
+    - redshift
+    - snowflake
+    - teradata
+    - tsql
+
+    # Generic conversions
+    - python
+    - scala
+    - airflow
+
+options:
+  all:
+    # Conversion settings
+    - flag: source_format
+      method: CHOICE
+      prompt: "Source file format"
+      choices: ["sql", "generic"]
+      default: "sql"
+    - flag: target_type
+      method: CHOICE
+      prompt: "Target output type"
+      choices: ["notebook", "file"]
+      default: "notebook"
+    - flag: output_extension
+      method: QUESTION
+      prompt: "Output file extension (for file target type) - press <enter> for none"
+      default: "<none>"
+
+    # Execution settings
+    - flag: endpoint_name
+      method: QUESTION
+      prompt: "Model endpoint name"
+      default: "databricks-claude-sonnet-4"
+    - flag: concurrency
+      method: QUESTION
+      prompt: "Concurrency level"
+      default: 4
+    - flag: max_fix_attempts
+      method: QUESTION
+      prompt: "Maximum fix attempts"
+      default: 1
+    - flag: log_level
+      method: CHOICE
+      prompt: "Log level"
+      choices: ["DEBUG", "INFO", "WARNING", "ERROR"]
+      default: "INFO"
+
+    # Advanced settings
+    - flag: token_count_threshold
+      method: QUESTION
+      prompt: "Token count threshold"
+      default: 20000
+    - flag: comment_lang
+      method: CHOICE
+      prompt: "Comment language"
+      choices: ["English", "Japanese", "Chinese", "French", "German", "Italian", "Korean", "Portuguese", "Spanish"]
+      default: "English"
+    - flag: conversion_prompt_yaml
+      method: QUESTION
+      prompt: "Custom conversion prompt YAML file path - press <enter> for default"
+      default: "<none>"
+    - flag: sql_output_dir
+      method: QUESTION
+      prompt: "SQL output directory - press <enter> for none"
+      default: "<none>"
+
+    # Complex optional parameters
+    - flag: request_params
+      method: QUESTION
+      prompt: "Additional request parameters (JSON) - press <enter> for none"
+      default: "<none>"
+
+    # Lakebridge CLI specific settings
+    - flag: wait_for_completion
+      method: CHOICE
+      prompt: "Wait for job completion?"
+      choices: ["true", "false"]
+      default: "false"
+
+# Custom configuration for Jobs API execution
+custom:
+  execution_type: "jobs_api"
+  job_id: null              # Populated after installation
+  job_name: null            # Populated after installation
+  job_url: null             # Populated after installation
+  switch_home: null         # Populated after installation
+  created_by: null          # Populated after installation