Combine markdown files from subdirectories in correct page order. Ignores files with duplicate page numbers and reports them. Only processes files that are exactly one subdirectory level deep.

combine_markdown.py

#!/usr/bin/env python3
"""
Combine markdown files from subdirectories in correct page order.
Ignores files with duplicate page numbers and reports them.
Only processes files that are exactly one subdirectory level deep.
"""

import os
import re
from pathlib import Path
from collections import defaultdict

def find_markdown_files(root_dir):
    """Find all markdown.md files exactly one subdirectory level deep."""
    markdown_files = []
    
    for item in os.scandir(root_dir):
        if item.is_dir():
            markdown_file = os.path.join(item.path, "markdown.md")
            if os.path.isfile(markdown_file):
                markdown_files.append(markdown_file)
    
    return markdown_files

def extract_page_number(file_path):
    """Extract page number from the first line of the file."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            first_line = f.readline().strip()
            # Extract only digits from the first line
            match = re.search(r'\d+', first_line)
            if match:
                return int(match.group())
            return None
    except Exception as e:
        print(f"Error reading {file_path}: {e}")
        return None

def combine_markdown_files(root_dir, output_file="combined.md"):
    """Combine markdown files in page order, handling duplicates."""
    # Find all markdown files
    markdown_files = find_markdown_files(root_dir)
    
    if not markdown_files:
        print("No markdown.md files found.")
        return
    
    # Extract page numbers and track duplicates
    page_info = []
    page_to_files = defaultdict(list)
    
    for file_path in markdown_files:
        page_num = extract_page_number(file_path)
        if page_num is not None:
            page_to_files[page_num].append(file_path)
    
    # Identify duplicates
    duplicates = {page: files for page, files in page_to_files.items() if len(files) > 1}
    
    if duplicates:
        print("Duplicate page numbers found (only first occurrence will be used):")
        for page, files in duplicates.items():
            print(f"  Page {page}: {', '.join([os.path.basename(os.path.dirname(f)) for f in files])}")
    
    # Sort by page number and get unique pages (first occurrence only)
    unique_pages = sorted(page_to_files.keys())
    
    print(f"\nCombining {len(unique_pages)} unique pages in order...")
    
    # Combine files in order
    with open(output_file, 'w', encoding='utf-8') as outfile:
        for page_num in unique_pages:
            # Use the first file for this page number
            file_path = page_to_files[page_num][0]
            
            with open(file_path, 'r', encoding='utf-8') as infile:
                content = infile.read()
                outfile.write(content)
                outfile.write("\n\n---\n\n")  # Add separator between pages
    
    print(f"\nCombined markdown file created: {output_file}")
    print(f"Total pages combined: {len(unique_pages)}")
    if duplicates:
        print(f"Duplicate pages ignored: {len(duplicates)}")

if __name__ == "__main__":
    # Get the current directory
    current_dir = os.path.dirname(os.path.abspath(__file__))
    
    print(f"Scanning for markdown files in: {current_dir}")
    print("=" * 60)
    
    combine_markdown_files(current_dir)
    
    print("\nDone!")