Metadata-Version: 2.1
Name: mdtidy
Version: 0.3.0
Summary: A Python library to clean and format markdown content into Jupyter Notebooks.
Home-page: https://github.com/davidkjeremiah/mdtidy
Author: David Jeremiah
Author-email: flasconnect@gmail.com
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# mdtidy

**mdtidy** is a Python library designed to clean and format markdown content from conversational AI outputs (specifically GPT and Gemini) into Jupyter Notebooks (.ipynb), while also counting code errors within the content. It's an intuitive tool for transforming raw markdown and code blocks into well-structured Jupyter notebooks, specifically tailored for reviewing AI-generated conversation data.

## Features

- **Markdown to Jupyter Notebook**: Convert markdown content with embedded Python code blocks into a Jupyter Notebook file.
- **Error Counting**: Identify and count common Python error types within the content.
- **Conversation Analysis**: Supports parsing and formatting conversation data from both GPT and Gemini models.

## Installation

Install mdtidy using pip:

```sh
pip install mdtidy
```

## Usage

### Convert GPT Conversations to Notebook

This example shows how to process GPT conversation data into a structured Jupyter notebook.

```python
from mdtidy.gpt_processor import process_gpt_conversation

# Trigger the processing of a GPT conversation, prompting for required details
process_gpt_conversation()
```

### Convert Gemini Conversations to Notebook

This example details processing Gemini model conversations into a notebook format, integrating error analysis.

```python
from mdtidy.gemini_processor import process_gemini_conversation

input_string_1 = """
# Insert the content of the first input string here, preserving its structure.
"""

input_string_2 = """
# Insert the content of the second input string here, preserving its structure.
"""

# Add more input strings as needed.

# Prepare your input strings for the Gemini model conversation
input_strings = [input_string_1, input_string_2]  # Extend this list as needed.
process_gemini_conversation(input_strings)
```

### Count Code Errors

This function identifies and counts typical Python errors within given content.

```python
from mdtidy.gemini_processor import count_code_errors

# Example content with typical Python errors
input_strings_with_errors = [
    """
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
NameError: name 'variable' is not defined

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: unsupported operand type(s) for +: 'int' and 'str'
"""
]

# Count and display code errors
error_counts = count_code_errors(input_strings_with_errors)
print(error_counts)
```

## License

This project is licensed under the MIT License - see the LICENSE file for details.
