This script parses text files containing code snippets extracted from gitingest.com and converts them into a CSV format for easier analysis and manipulation.

gitingest_to_csv.py

"""
# GitIngest Code Extractor

## Description
This script parses text files containing code snippets extracted from gitingest.com 
and converts them into a CSV format for easier analysis and manipulation.

## Purpose
When downloading code from gitingest.com, files are often consolidated into a single
text file with delimiters separating each code file. This script identifies these
delimiters (lines of equal signs followed by file paths) and extracts each code file
into a separate cell in a CSV file.

## Input Format
The script expects text files structured as follows:
```
================================================
File: path/to/file1.ext
================================================
[Content of file1]

================================================
File: path/to/file2.ext
================================================
[Content of file2]
```

## Output Format
The script produces a CSV file with a single column named 'content'.
Each cell contains:
1. The file path from the original file
2. The complete code content of that file

This format makes it easier to:
- Import the code into spreadsheet applications
- Perform further analysis on the codebase
- Share code extracts in a structured format

## Usage
1. Save your gitingest.com extracted text to a file (default: "uniswap_code.txt")
2. Run this script
3. Access the organized code in the output CSV (default: "uniswap_code.csv")
"""

import csv
import re

def parse_code_to_csv(input_file, output_file):
    # Read the input file
    with open(input_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Define a pattern to match file sections
    # This pattern matches everything between a file header and the next file header or end of file
    pattern = r'={48}\s*File:\s*(.*?)\s*={48}(.*?)(?=={48}|$)'
    
    # Find all matches
    matches = re.findall(pattern, content, re.DOTALL)
    
    # Prepare data for CSV
    code_files = []
    for file_path, code_content in matches:
        # Combine file path and code content into a single field
        combined_content = f"File: {file_path.strip()}\n{code_content.strip()}"
        code_files.append([combined_content])
    
    # Write to CSV
    with open(output_file, 'w', newline='', encoding='utf-8') as csvfile:
        writer = csv.writer(csvfile)
        
        # Write header
        writer.writerow(['content'])
        
        # Write each file's content to a single cell
        for file_data in code_files:
            writer.writerow(file_data)
    
    return len(code_files)

if __name__ == "__main__":
    input_file = "gitingest_code.txt"  # Change this to your input file path
    output_file = "gitingest_code.csv"  # Change this to your desired output file path
    
    num_files = parse_code_to_csv(input_file, output_file)
    print(f"Successfully extracted {num_files} code files to {output_file}")