markitect-main/markitect/plugins/builtin/markdown_commands.py

"""
Markdown commands plugin for MarkiTect.

This plugin provides the core markdown file operations with md- prefixes,
replacing the legacy unprefixed commands for better namespace consistency.
"""

import click
from pathlib import Path
from typing import Dict, Any

from markitect.plugins.base import CommandPlugin, PluginMetadata, PluginType
from markitect.plugins.decorators import register_plugin
from markitect.document_manager import DocumentManager
from markitect.serializer import ASTSerializer
# Simple helper function - avoiding circular imports
def get_default_format(available_formats=['table', 'json', 'yaml', 'simple'], fallback='simple'):
    """Get the default output format - simplified version for plugin."""
    return fallback


@register_plugin("markdown_commands")
class MarkdownCommandsPlugin(CommandPlugin):
    """Plugin providing core markdown file operations."""

    @property
    def metadata(self) -> PluginMetadata:
        return PluginMetadata(
            name="markdown_commands",
            version="1.0.0",
            description="Core markdown file operations (ingest, get, list) with md- prefixes",
            author="MarkiTect Core Team",
            plugin_type=PluginType.COMMAND,
            markitect_version=">=0.1.0"
        )

    def get_commands(self) -> Dict[str, Any]:
        """Return the markdown commands with md- prefixes."""
        return {
            'md-ingest': md_ingest_command,
            'md-get': md_get_command,
            'md-list': md_list_command
        }


# Define commands as standalone functions

@click.command()
@click.argument('file_path', type=click.Path(exists=True))
@click.pass_context
def md_ingest_command(ctx, file_path):
    """
    Process and store a markdown file.

    Ingests a markdown file into the MarkiTect system, parsing its content,
    extracting front matter, generating AST cache, and storing metadata
    in the database.

    FILE_PATH: Path to the markdown file to process

    Examples:
        markitect md-ingest README.md
        markitect md-ingest docs/guide.md
    """
    config = ctx.obj or {}
    try:
        if config.get('verbose', False):
            click.echo(f"Processing file: {file_path}")

        # Initialize document manager with database manager
        doc_manager = DocumentManager(config.get('db_manager'))

        # Process the file
        result = doc_manager.ingest_file(file_path)

        if config.get('verbose', False):
            click.echo(f"Processing results:")
            click.echo(f"  File: {result['metadata']['filename']}")
            click.echo(f"  AST nodes: {len(result['ast'])} nodes")
            click.echo(f"  Cache file: {result['ast_cache_path']}")
            click.echo(f"  Parse time: {result['parse_time']:.2f}s")
            click.echo(f"  Cache time: {result['cache_time']:.2f}s")

        click.echo(f"✓ Successfully ingested: {Path(file_path).name}")

    except Exception as e:
        click.echo(f"Error processing file: {e}", err=True)
        raise click.Abort()


@click.command()
@click.argument('file_path', type=str)
@click.option('--output', '-o', type=click.Path(), help='Output file path (default: stdout)')
@click.pass_context
def md_get_command(ctx, file_path, output):
    """
    Retrieve and output a processed markdown file.

    Loads the file from the database and AST cache, then serializes it back
    to markdown format. Supports outputting to file or stdout.

    FILE_PATH: Name of the file to retrieve

    Examples:
        markitect md-get README.md
        markitect md-get docs/guide.md --output modified_guide.md
    """
    config = ctx.obj or {}
    try:
        if config.get('verbose', False):
            click.echo(f"Retrieving file: {file_path}")

        db_manager = config.get('db_manager')

        # Get file information from database
        file_info = db_manager.get_markdown_file(file_path)
        if not file_info:
            click.echo(f"File not found in database: {file_path}", err=True)
            click.echo("Use 'markitect md-ingest' to process the file first.", err=True)
            raise click.Abort()

        # Load AST from cache
        cache_filename = f"{file_path}.ast.json"
        cache_path = Path('.ast_cache') / cache_filename

        if not cache_path.exists():
            click.echo(f"AST cache not found: {cache_path}", err=True)
            click.echo("Try re-ingesting the file to regenerate cache.", err=True)
            raise click.Abort()

        # Read AST from cache
        import json
        with open(cache_path, 'r', encoding='utf-8') as f:
            ast = json.load(f)

        # Parse front matter from database
        front_matter = None
        if file_info.get('front_matter'):
            try:
                front_matter = eval(file_info['front_matter'])
            except (ValueError, TypeError, SyntaxError):
                if config.get('verbose', False):
                    click.echo("Warning: Could not parse front matter", err=True)

        # Serialize AST back to markdown
        serializer = ASTSerializer()
        markdown_content = serializer.serialize_to_markdown(ast, front_matter)

        # Output to file or stdout
        if output:
            output_path = Path(output)
            output_path.parent.mkdir(parents=True, exist_ok=True)
            with open(output_path, 'w', encoding='utf-8') as f:
                f.write(markdown_content)
            click.echo(f"✓ File written to: {output_path}")
        else:
            click.echo(markdown_content)

        if config.get('verbose', False):
            click.echo(f"Retrieved {len(ast)} AST tokens", err=True)

    except Exception as e:
        click.echo(f"Error retrieving file: {e}", err=True)
        raise click.Abort()


@click.command()
@click.option('--format', 'output_format', type=click.Choice(['table', 'json', 'yaml', 'simple']),
              default=lambda: get_default_format(['table', 'json', 'yaml', 'simple']), help='Output format')
@click.option('--names-only', is_flag=True, help='Show only filenames (no metadata)')
@click.pass_context
def md_list_command(ctx, output_format, names_only):
    """
    List all stored markdown files and their status.

    Shows all markdown files that have been processed and stored
    in the MarkiTect database with their basic metadata.

    Examples:
        markitect md-list
        markitect md-list --format table
        markitect md-list --format json
        markitect md-list --names-only
    """
    config = ctx.obj or {}
    try:
        if config.get('verbose', False):
            click.echo("Retrieving all stored files...")

        db_manager = config.get('db_manager')
        files = db_manager.list_markdown_files()

        if not files:
            click.echo("No files found in database.")
            click.echo("Use 'markitect md-ingest <file>' to add files.")
            return

        # Handle names-only option
        if names_only:
            for file_info in files:
                click.echo(file_info['filename'])
            return

        # Handle different output formats
        if output_format == 'simple':
            # Original emoji format
            click.echo(f"Found {len(files)} file(s):")
            click.echo()

            for file_info in files:
                click.echo(f"📄 {file_info['filename']}")
                if config.get('verbose', False):
                    click.echo(f"   Created: {file_info['created_at']}")
                    if file_info.get('front_matter'):
                        try:
                            front_matter = eval(file_info['front_matter'])
                            if front_matter:
                                click.echo(f"   Front matter: {list(front_matter.keys())}")
                        except (ValueError, TypeError, SyntaxError):
                            click.echo(f"   Front matter: (parsing error)")
                    click.echo()
        else:
            # Use structured format (table, json, yaml)
            if output_format == 'json':
                import json
                click.echo(json.dumps(files, indent=2, default=str))
            elif output_format == 'yaml':
                import yaml
                click.echo(yaml.dump(files, default_flow_style=False))
            else:  # table format (default)
                # Simple table output
                click.echo(f"Found {len(files)} file(s):")
                click.echo(f"{'Filename':<30} {'Created':<20}")
                click.echo("-" * 50)
                for file_info in files:
                    click.echo(f"{file_info['filename']:<30} {file_info['created_at']:<20}")

    except Exception as e:
        click.echo(f"Error listing files: {e}", err=True)
        raise click.Abort()