ETPlot/orchestration/metadata.py

"""
Metadata Management for Scientific Gallery Generator

This module handles loading, parsing, and caching of metadata for plots
and folders in the gallery system. Supports YAML and JSON formats with
hierarchical inheritance.

Features:
- Load metadata from YAML/JSON files
- Hierarchical metadata inheritance from parent folders
- Plot-specific metadata overrides
- Metadata caching for performance
"""

import json
import yaml
import logging
from pathlib import Path
from typing import Dict, Any


def load_metadata_file(metadata_path: Path) -> Dict[str, Any]:
    """
    Load metadata from a YAML or JSON file.

    Args:
        metadata_path: Path to the metadata file

    Returns:
        Dictionary containing the metadata, empty dict if file doesn't exist
        or can't be parsed
    """
    if not metadata_path.exists():
        return {}

    try:
        with metadata_path.open('r', encoding='utf-8') as f:
            suffix_lower = metadata_path.suffix.lower()
            if suffix_lower == '.yaml' or suffix_lower == '.yml':
                return yaml.safe_load(f) or {}
            elif metadata_path.suffix.lower() == '.json':
                return json.load(f) or {}
            else:
                logging.warning(f"Unknown metadata file format: {metadata_path}")
                return {}
    except (yaml.YAMLError, json.JSONDecodeError, IOError) as e:
        logging.warning(f"Could not parse metadata file {metadata_path}: {e}")
        raise e


def load_folder_metadata(folder_path: Path) -> Dict[str, Any]:
    """
    Load folder-level metadata from metadata.yaml, metadata.yml, or metadata.json.

    Args:
        folder_path: Path to the folder to check for metadata

    Returns:
        Dictionary containing the folder metadata
    """
    # Try YAML first, then JSON for backwards compatibility
    for filename in ['metadata.yaml', 'metadata.yml', 'metadata.json']:
        metadata_path = folder_path / filename
        if metadata_path.exists():
            return load_metadata_file(metadata_path)

    return {}


def get_metadata_file_path(folder_path: Path) -> str:
    """
    Get the metadata file path for a folder. Returns existing file if found,
    otherwise suggests metadata.yaml (preferred format).

    Args:
        folder_path: Path to the folder to check for metadata

    Returns:
        String path to the metadata file (existing or suggested)
    """
    # Preferred order: YAML first, then JSON
    preferred_files = ['metadata.yaml', 'metadata.yml', 'metadata.json']
        
    for filename in preferred_files:
        metadata_path = folder_path / filename
        if metadata_path.exists():
            return str(metadata_path)
    
    # If no file exists, suggest metadata.yaml (preferred format)
    return str(folder_path / 'metadata.yaml')


def merge_metadata(
    parent_metadata: Dict[str, Any],
    child_metadata: Dict[str, Any]
) -> Dict[str, Any]:
    """
    Merge parent and child metadata, with child values overriding parent
    values.

    Args:
        parent_metadata: Metadata from parent folder
        child_metadata: Metadata from current folder

    Returns:
        Merged metadata dictionary
    """
    merged = parent_metadata.copy()
    merged.update(child_metadata)
    return merged


def resolve_metadata_for_plot(
    plot_path: Path,
    inherited_metadata: Dict[str, Any]
) -> Dict[str, Any]:
    """
    Resolve metadata for a specific plot by merging inherited metadata
    with plot-specific metadata.

    Args:
        plot_path: Path to the plot file (PDF)
        inherited_metadata: Metadata inherited from folder hierarchy

    Returns:
        Final merged metadata for the plot
    """
    plot_stem = plot_path.stem
    plot_dir = plot_path.parent

    # Check for plot-specific metadata files
    for suffix in ['.yaml', '.yml', '.json']:
        plot_metadata_path = plot_dir / f"{plot_stem}{suffix}"
        if plot_metadata_path.exists():
            plot_metadata = load_metadata_file(plot_metadata_path)
            return merge_metadata(inherited_metadata, plot_metadata)

    # No plot-specific metadata found, return inherited metadata
    return inherited_metadata.copy()


def save_metadata_cache(
    web_dir: Path,
    plot_metadata_cache: Dict[str, Dict[str, Any]]
) -> None:
    """
    Save plot metadata cache to meta_cache.json in the web directory.

    Args:
        web_dir: Web directory where the cache file should be saved
        plot_metadata_cache: Dictionary mapping plot names to their metadata
    """
    cache_path = web_dir / "meta_cache.json"
    try:
        with cache_path.open('w', encoding='utf-8') as f:
            json.dump(plot_metadata_cache, f, indent=2, ensure_ascii=False)
        logging.debug(f"Saved metadata cache: {cache_path}")
    except IOError as e:
        logging.warning(f"Could not save metadata cache {cache_path}: {e}")