montpelliermaalsi2024/obsidian/bin/obsidian_converter.py

#!/usr/bin/env python3
"""
Convert Obsidian-style wiki links to standard markdown links.

This script processes markdown files containing Obsidian wiki links in the format:
- [[ mypage ]] -> [mypage](mypage.md)
- [[ myfolder/mypage ]] -> [myfolder/mypage](myfolder/mypage.md)
- [[ myfolder/mypage | my description ]] -> [my description](myfolder/mypage.md)

Usage:
    python obsidian_converter.py source_folder destination_folder
"""

import os
import re
import sys
import shutil
import argparse
from pathlib import Path


def build_file_index(source_folder):
    """
    Build an index of all markdown files in the source folder.
    Maps filename (without extension) to full relative paths.
    
    Args:
        source_folder (Path): Root folder to index
        
    Returns:
        dict: Map of filename -> list of relative paths
    """
    file_index = {}
    
    for md_file in source_folder.rglob('*.md'):
        relative_path = md_file.relative_to(source_folder)
        filename = md_file.stem  # filename without extension
        
        if filename not in file_index:
            file_index[filename] = []
        file_index[filename].append(relative_path)
    
    return file_index


def convert_wiki_links(content, file_index, current_file_path, source_folder):
    """
    Convert wiki-style links to standard markdown links with relative paths.
    
    Args:
        content (str): The markdown content to process
        file_index (dict): Map of filenames to their paths
        current_file_path (Path): Path of the current file being processed (relative to source)
        source_folder (Path): Root source folder
        
    Returns:
        tuple: (converted_content, list of warnings)
    """
    # Pattern to match wiki links: [[ link ]] or [[ link | description ]]
    # Group 1: the link path
    # Group 2: optional description (after |)
    wiki_link_pattern = r'\[\[\s*([^|\]]+?)(?:\s*\|\s*([^\]]+?))?\s*\]\]'
    
    warnings = []
    
    def replace_wiki_link(match):
        link_path = match.group(1).strip()
        description = match.group(2)
        
        # If there's a custom description, use it; otherwise use the link text
        if description:
            display_text = description.strip()
        else:
            # Extract just the filename for display (without folder path)
            display_text = os.path.basename(link_path)
        
        # Check if the link already includes a path separator
        if '/' in link_path or '\\' in link_path:
            # User specified a path - use it as-is
            target_path = link_path
            if not target_path.endswith('.md'):
                target_path += '.md'
            
            # Verify the file exists
            full_path = source_folder / target_path
            if not full_path.exists():
                warnings.append(f"File not found for link '[[ {link_path} ]]' -> {target_path}")
                return f'[{display_text}]({target_path})'
            
            # Convert to relative path
            target_path = Path(target_path)
        else:
            # Just a filename - search for it
            filename = link_path
            
            if filename in file_index:
                paths = file_index[filename]
                
                if len(paths) == 1:
                    # Single match - use it
                    target_path = paths[0]
                else:
                    # Multiple matches - warn and use the first one
                    target_path = paths[0]
                    paths_list = '\n    '.join(str(p) for p in paths)
                    warnings.append(
                        f"Multiple files found for '[[ {filename} ]]':\n    {paths_list}\n  Using: {target_path}"
                    )
            else:
                # File not found
                warnings.append(f"File not found for link '[[ {link_path} ]]' - no matching .md file")
                # Still create a link, but it will be broken
                target_path = link_path
                if not target_path.endswith('.md'):
                    target_path += '.md'
                return f'[{display_text}]({target_path})'
        
        # Calculate relative path from current file to target file
        # current_file_path is relative to source_folder (e.g., 'notes/index.md')
        # target_path is also relative to source_folder (e.g., 'reference/MyPage.md')
        
        current_dir = current_file_path.parent
        
        # Calculate relative path
        try:
            relative_path = os.path.relpath(target_path, current_dir)
            # Normalize path separators to forward slashes for markdown
            relative_path = relative_path.replace('\\', '/')
        except ValueError:
            # Fallback if relpath fails (different drives on Windows)
            relative_path = str(target_path)
        
        return f'[{display_text}]({relative_path})'
    
    # Replace all wiki links with standard markdown links
    converted_content = re.sub(wiki_link_pattern, replace_wiki_link, content)
    
    return converted_content, warnings


def process_markdown_file(source_path, dest_path, file_index, source_folder, dry_run=False, verbose=False):
    """
    Process a single markdown file, converting wiki links.
    
    Args:
        source_path (Path): Source file path
        dest_path (Path): Destination file path
        file_index (dict): Map of filenames to their paths
        source_folder (Path): Root source folder
        dry_run (bool): If True, don't actually write files
        verbose (bool): If True, show detailed output
        
    Returns:
        tuple: (conversions_made, list of warnings)
    """
    try:
        with open(source_path, 'r', encoding='utf-8') as f:
            content = f.read()
        
        # Calculate relative path from source folder for this file
        relative_file_path = source_path.relative_to(source_folder)
        
        # Convert wiki links
        converted_content, warnings = convert_wiki_links(content, file_index, relative_file_path, source_folder)
        
        # Check if any conversions were made
        conversions_made = content != converted_content
        
        if dry_run:
            status = "WOULD CONVERT" if conversions_made else "NO CHANGES"
            print(f"{status}: {source_path} -> {dest_path}")
            if verbose and conversions_made:
                # Show what wiki links were found
                wiki_links = re.findall(r'\[\[\s*([^|\]]+?)(?:\s*\|\s*([^\]]+?))?\s*\]\]', content)
                for link in wiki_links:
                    if link[1]:  # Has custom description
                        print(f"  [[ {link[0]} | {link[1]} ]]")
                    else:
                        print(f"  [[ {link[0]} ]]")
            if warnings and verbose:
                for warning in warnings:
                    print(f"  ⚠ {warning}")
        else:
            # Ensure destination directory exists
            dest_path.parent.mkdir(parents=True, exist_ok=True)
            
            # Write converted content
            with open(dest_path, 'w', encoding='utf-8') as f:
                f.write(converted_content)
            
            if verbose or conversions_made:
                status = "CONVERTED" if conversions_made else "COPIED"
                print(f"{status}: {source_path} -> {dest_path}")
        
        # Display warnings for this file
        if warnings:
            print(f"⚠ WARNING in {source_path.relative_to(source_folder)}:")
            for warning in warnings:
                print(f"  {warning}")
        
        return conversions_made, warnings
        
    except Exception as e:
        print(f"ERROR processing {source_path}: {e}")
        return False, []


def main():
    """Main function to handle command line arguments and process files."""
    parser = argparse.ArgumentParser(
        description="Convert Obsidian-style wiki links to standard markdown links.",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
  python obsidian_converter.py ./my_obsidian_vault ./converted_markdown
  python obsidian_converter.py /path/to/obsidian /path/to/output

Wiki link conversion examples:
  [[ mypage ]]                    -> [mypage](mypage.md)
  [[ myfolder/mypage ]]           -> [myfolder/mypage](myfolder/mypage.md)
  [[ myfolder/mypage | My Title ]] -> [My Title](myfolder/mypage.md)
        """
    )
    
    parser.add_argument(
        'source_folder',
        help='Source folder containing Obsidian markdown files'
    )
    
    parser.add_argument(
        'destination_folder',
        help='Destination folder for converted markdown files'
    )
    
    parser.add_argument(
        '--dry-run',
        action='store_true',
        help='Show what would be converted without actually converting files'
    )
    
    parser.add_argument(
        '--verbose', '-v',
        action='store_true',
        help='Show detailed output during conversion'
    )
    
    args = parser.parse_args()
    
    source_folder = Path(args.source_folder)
    dest_folder = Path(args.destination_folder)
    
    # Validate source folder
    if not source_folder.exists():
        parser.error(f"Source folder '{source_folder}' does not exist.")
    
    if not source_folder.is_dir():
        parser.error(f"'{source_folder}' is not a directory.")
    
    # Create destination folder if it doesn't exist (unless dry run)
    if not args.dry_run:
        dest_folder.mkdir(parents=True, exist_ok=True)
    
    action = "Would convert" if args.dry_run else "Converting"
    print(f"{action} Obsidian markdown files from '{source_folder}' to '{dest_folder}'")
    if args.dry_run:
        print("(DRY RUN - no files will be modified)")
    print("-" * 60)
    
    # Build file index
    print("Building file index...")
    file_index = build_file_index(source_folder)
    print(f"Indexed {len(file_index)} unique markdown files")
    print("-" * 60)
    
    # Track statistics
    total_files = 0
    converted_files = 0
    files_with_conversions = 0
    all_warnings = []
    
    # Process all markdown files recursively
    for source_path in source_folder.rglob('*.md'):
        total_files += 1
        
        # Calculate relative path to maintain folder structure
        relative_path = source_path.relative_to(source_folder)
        dest_path = dest_folder / relative_path
        
        # Process the file
        had_conversions, warnings = process_markdown_file(
            source_path, dest_path, 
            file_index, source_folder,
            dry_run=args.dry_run, 
            verbose=args.verbose
        )
        
        converted_files += 1
        if had_conversions:
            files_with_conversions += 1
        
        all_warnings.extend(warnings)
    
    # Copy non-markdown files as well (images, etc.) - unless dry run
    non_md_files = 0
    if not args.dry_run:
        for source_path in source_folder.rglob('*'):
            if source_path.is_file() and not source_path.suffix == '.md':
                relative_path = source_path.relative_to(source_folder)
                dest_path = dest_folder / relative_path
                
                # Ensure destination directory exists
                dest_path.parent.mkdir(parents=True, exist_ok=True)
                
                # Copy the file
                shutil.copy2(source_path, dest_path)
                non_md_files += 1
                if args.verbose:
                    print(f"COPIED: {source_path} -> {dest_path}")
    
    print("-" * 60)
    if args.dry_run:
        print("Dry run complete!")
        print(f"Total markdown files: {total_files}")
        print(f"Files with wiki links to convert: {files_with_conversions}")
    else:
        print("Conversion complete!")
        print(f"Total markdown files processed: {converted_files}/{total_files}")
        print(f"Files with wiki links converted: {files_with_conversions}")
        if non_md_files > 0:
            print(f"Non-markdown files copied: {non_md_files}")
        print(f"Output directory: {dest_folder}")
    
    # Summary of warnings
    if all_warnings:
        print("-" * 60)
        print(f"⚠ TOTAL WARNINGS: {len(all_warnings)}")
        print("Review the warnings above to fix broken links.")


if __name__ == "__main__":
    main()