gemini-code-assist[bot] commented on PR #37665:
URL: https://github.com/apache/beam/pull/37665#issuecomment-3937111135

   ## Summary of Changes
   
   Hello @derrickaw, I'm Gemini Code Assist[^1]! I'm currently reviewing this 
pull request and will post my feedback shortly. In the meantime, here's a 
summary to help you and other reviewers quickly get up to speed!
   
   This pull request reverses a prior change, restoring `js2py` as the 
JavaScript execution engine for YAML-based UDFs within Apache Beam. The primary 
goal is to ensure compatibility and stability by reverting the integration of 
`pythonmonkey` and re-establishing the `js2py` framework, including necessary 
adaptations for object serialization and dependency management.
   
   ### Highlights
   
   * **Reverted JavaScript Engine**: The pull request reverts the JavaScript 
execution engine used in Apache Beam's YAML module from `pythonmonkey` back to 
`js2py`.
   * **Dependency Management**: The `setup.py` file was updated to remove the 
`pythonmonkey` dependency and reintroduce `js2py`, with a version constraint 
and a condition for Python versions less than 3.12.
   * **Codebase Cleanup**: Extensive `pythonmonkey`-related code, including a 
custom dispatcher and callable classes, was removed from `yaml_mapping.py`. 
Corresponding `js2py` imports and logic were reinstated.
   * **Pickling Support for js2py**: A custom `_CustomJsObjectWrapper` class 
was added to `yaml_mapping.py` to address pickling issues with 
`js2py.JsObjectWrapper` objects.
   * **Test Updates**: Unit tests in `yaml_udf_test.py` were adjusted to 
reflect the switch back to `js2py`, updating import checks and skip conditions.
   
   🧠 **New Feature in Public Preview:** You can now enable **Memory** to help 
**Gemini Code Assist** learn from your team's feedback. This makes future code 
reviews more consistent and personalized to your project's style. **Click 
[here](https://codeassist.google/code-review/login) to enable Memory in your 
admin console.**
   
   <details>
   <summary><b>Changelog</b></summary>
   
   * **sdks/python/apache_beam/yaml/standard_io.yaml**
       * Removed `num_shards` parameter from the `WriteToJson` transform 
definition.
   * **sdks/python/apache_beam/yaml/yaml_mapping.py**
       * Removed imports related to `atexit`, `importlib`, `os`, `queue`, 
`sys`, `threading`, and `uuid`.
       * Reintroduced conditional imports for `js2py` and `JsObjectWrapper`.
       * Added `_CustomJsObjectWrapper` class to provide pickling support for 
`js2py` objects.
       * Removed the `PythonMonkeyDispatcher` and `JavaScriptCallable` classes.
       * Refactored `_expand_javascript_mapping_func` to use `js2py` for 
JavaScript evaluation and result conversion, including a new 
`_js_object_to_py_object` helper function.
       * Updated the error message for missing JavaScript support to reference 
`js2py` and Python 3.12 compatibility.
   * **sdks/python/apache_beam/yaml/yaml_udf_test.py**
       * Removed `importlib` import.
       * Updated the JavaScript engine availability check from `pythonmonkey` 
to `js2py`.
       * Modified `unittest.skipIf` decorators to check for `js2py` 
installation status.
   * **sdks/python/setup.py**
       * Replaced the `pythonmonkey` dependency with `js2py`, specifying a 
version range (`>=0.74,<1`) and a Python version constraint 
(`python_version<"3.12"`).
   </details>
   
   <details>
   <summary><b>Using Gemini Code Assist</b></summary>
   <br>
   
   The full guide for Gemini Code Assist can be found on our [documentation 
page](https://developers.google.com/gemini-code-assist/docs/review-github-code),
 here are some quick tips.
   
   <b>Invoking Gemini</b>
   
   You can request assistance from Gemini at any point by creating a comment 
using either `/gemini <command>` or `@gemini-code-assist <command>`. Below is a 
summary of the supported commands on the current page.
   
   Feature | Command | Description
   --- | --- | ---
   Code Review | `/gemini review` | Performs a code review for the current pull 
request in its current state.
   Pull Request Summary | `/gemini summary` | Provides a summary of the current 
pull request in its current state.
   Comment | @gemini-code-assist | Responds in comments when explicitly tagged, 
both in pull request comments and review comments.
   Help | `/gemini help` | Displays a list of available commands.
   
   <b>Customization</b>
   
   To customize Gemini Code Assist for GitHub experience, repository 
maintainers can create a configuration file and/or provide a custom code review 
style guide (such as PEP-8 for Python) by creating and adding files to a 
`.gemini/` folder in the base of the repository. Detailed instructions can be 
found 
[here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github).
   
   <b>Limitations & Feedback</b>
   
   Gemini Code Assist may make mistakes. Please leave feedback on any instances 
where its feedback is incorrect or counter productive. You can react with 
:thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're 
interested in giving your feedback about your experience with Gemini Code 
Assist for Github and other Google products, sign up 
[here](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG).
   
   <b>You can also get AI-powered code generation, chat, as well as code 
reviews directly in the IDE at no cost with the [Gemini Code Assist IDE 
Extension](https://cloud.google.com/products/gemini/code-assist).</b>
   </details>
   
   
   [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), 
[Generative AI Prohibited Use 
Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of 
Service](https://policies.google.com/terms), and learn how to configure Gemini 
Code Assist in GitHub 
[here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github).
 Gemini can make mistakes, so double check it and [use code with 
caution](https://support.google.com/legal/answer/13505487).
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to