Retrieve specific bicep modules for AI use.

retrieveModules.py

import requests
import re

def extract_bicep_lines(content):
    # Extract lines that match the pattern '- **bicep'
    bicep_lines = []
    for line in content.splitlines():
        if line.startswith('- **bicep'):
            bicep_lines.append(line)
    
    # Print each extracted Bicep line with its line number
    for index, bicep_line in enumerate(bicep_lines, start=1):
        print(f"{index}: {bicep_line}")
    return bicep_lines

def fetch_markdown_blocks(content, bicep_lines, identifier, selected_blocks):
    print()  # Add newline after input before showing results
    
    # Check if the identifier is a number (line number)
    if identifier.isdigit():
        filtered_index = int(identifier) - 1  # Convert to zero-based index
        if hasattr(fetch_markdown_blocks, 'current_filtered_lines'):
            # Use the stored filtered lines
            if 0 <= filtered_index < len(fetch_markdown_blocks.current_filtered_lines):
                line = fetch_markdown_blocks.current_filtered_lines[filtered_index]
            else:
                print(f"Line number {identifier} is out of range.")
                return
        else:
            # Use the original list if no filtering has been done
            if 0 <= filtered_index < len(bicep_lines):
                line = bicep_lines[filtered_index]
            else:
                print(f"Line number {identifier} is out of range.")
                return

        # Extract the module name from the line
        module_name = re.search(r'\*\*(.*?)\*\*', line).group(1).replace('/', '_').replace(' ', '_')
        
        # Find the full section in the content
        pattern = rf'({re.escape(line)}.*?```bicep.*?```)'
        match = re.search(pattern, content, re.DOTALL)
        
        if match:
            # Store the full block (including header and code)
            selected_blocks[module_name] = match.group(1)
            print(f"Block for {module_name} has been selected for writing")
        else:
            print(f"No full match found for line: {line}")
    else:
        # Filter lines that match the search text
        matching_lines = [line for line in bicep_lines if identifier.lower() in line.lower()]
        # Store the filtered lines for later use
        fetch_markdown_blocks.current_filtered_lines = matching_lines
        
        print(f"Matching Lines for '{identifier}':")
        if matching_lines:
            for index, line in enumerate(matching_lines, start=1):
                print(f"{index}: {line}")
        else:
            print(f"No matches found for '{identifier}'")

def write_selected_blocks(selected_blocks):
    if not selected_blocks:
        print("No blocks were selected.")
        return

    # Write all selected blocks to a single file
    with open("modules.md", 'w') as file:
        for module_name, block in selected_blocks.items():
            file.write(f"{block}\n\n")
    print("All selected blocks have been written to modules.md")

# Main loop for user input
if __name__ == "__main__":
    # Fetch the content from the URL once at startup
    url = "https://gist.githubusercontent.com/danielscholl/1b0028e9af9f5304c4f6e0cea064c3e2/raw/cce2e41a1f32a84a1a6c129344145035b110c62b/modules.md"
    print(f"Retrieving data from {url}...")
    response = requests.get(url)
    content = response.text

    # Extract lines that match the pattern '- **bicep'
    bicep_lines = extract_bicep_lines(content)
    
    # Dictionary to store selected blocks
    selected_blocks = {}

    while True:
        identifier = input("Enter a line number to retrieve the module or text to filter (or press Enter to quit): ").strip()
        if not identifier:  # Exit if input is empty
            print("\nWriting selected blocks to file...")
            write_selected_blocks(selected_blocks)
            print("Exiting the program.")
            break
        fetch_markdown_blocks(content, bicep_lines, identifier, selected_blocks)