Improved Language Detection Functionality (Tasks 1-3)

[amit828as]

Task 1: Core Language Detection Function (pypacter/src/pypacter.py)

This pull request implements three new features for Pypacter, enhancing its language detection capabilities:

A new function, detect_programming_language(code_snippet: str) -> str, has been added to the core Pypacter package. This function takes a code snippet as input and uses the DEFAULT_MODEL from the pypacter.models module to analyze it with a Large Language Model (LLM). The detected programming language is returned.

The LLM prompt has been carefully crafted to handle various scenarios:

1. It explicitly states the provided code snippet.
2. It acknowledges the possibility of non-programming languages or invalid syntax.
3. It requests only the programming language name without explanations.

Task 2: Language Detection API Endpoint (pypacter-api/src/pypacter_api/api.py)

A new API endpoint, /detect-language, has been added to the pypacter-api package. This endpoint accepts a POST request with a JSON body containing the code_snippet field. It performs the following actions:

1. Validates the presence of the code_snippet parameter.
2. Calls the detect_programming_language function from the core package.
3. Returns a JSON response containing the detected language (lowercase) on success.
4. Raises appropriate HTTP exceptions for missing code snippets or language detection failures.

Task 3: Language Detection CLI Command (pypacter-cli/src/pypacter_cli/cli.py)

A new CLI command, detect-language, has been added to the pypacter-cli package. This command allows users to detect the programming language of a code snippet through the command line. It offers two ways to provide the code snippet:

1. As a file path passed as an argument.
2. Through standard input using pipes (|).
3. The command interacts with the detect_programming _language function and presents the detected language in a user-friendly format.

These enhancements have been implemented with a focus on the provided guidelines:

• Readability and Clarity: The code adheres to best practices for naming conventions, structure, and comments. Documentation is included for all new features.
• Correctness: The code handles edge cases like missing code snippets and potential LLM errors gracefully. Unit tests ensure functionality.
• Maintainability: The code is modular and extensible, allowing for future improvements to the language detection mechanism.

Next Steps:

• Consider exploring alternative LLM access methods or implementing a fallback mechanism for potential LLM limitations.
• Investigate integrating the language detection functionality with other Pypacter features.

Please reach out if there has been any kind of oversight from my end.