mindnet/app/services/edge_registry.py

"""
FILE: app/services/edge_registry.py
DESCRIPTION: Single Source of Truth für Kanten-Typen. Parst '01_User_Manual/01_edge_vocabulary.md'.
             WP-22 Teil B: Registry & Validation.
             Beachtet den dynamischen Vault-Root aus ENV oder Parameter.
"""
import re
import os
import json
import logging
from typing import Dict, Optional, Set

from app.config import get_settings

logger = logging.getLogger(__name__)

class EdgeRegistry:
    _instance = None

    def __new__(cls, vault_root: Optional[str] = None):
        if cls._instance is None:
            cls._instance = super(EdgeRegistry, cls).__new__(cls)
            cls._instance.initialized = False
        return cls._instance

    def __init__(self, vault_root: Optional[str] = None):
        if self.initialized: 
            return
            
        settings = get_settings()
        # Priorität: 1. Parameter (Test) -> 2. Config (.env) -> 3. Default
        self.vault_root = vault_root or getattr(settings, "MINDNET_VAULT_ROOT", "./vault")
        self.vocab_rel_path = os.path.join("01_User_Manual", "01_edge_vocabulary.md")
        self.unknown_log_path = "data/logs/unknown_edges.jsonl"
        
        self.canonical_map: Dict[str, str] = {} 
        self.valid_types: Set[str] = set()
        
        self._load_vocabulary()
        self.initialized = True

    def _load_vocabulary(self):
        """Parst die Markdown-Tabelle im Vault."""
        full_path = os.path.abspath(os.path.join(self.vault_root, self.vocab_rel_path))
        
        if not os.path.exists(full_path):
            logger.warning(f"Edge Vocabulary NOT found at: {full_path}. Registry is empty.")
            return

        # Regex für Markdown Tabellen: | **canonical** | Aliases | ...
        pattern = re.compile(r"\|\s*\*\*([a-z_]+)\*\*\s*\|\s*([^|]+)\|")

        try:
            with open(full_path, "r", encoding="utf-8") as f:
                for line in f:
                    match = pattern.search(line)
                    if match:
                        canonical = match.group(1).strip()
                        aliases_str = match.group(2).strip()
                        
                        self.valid_types.add(canonical)
                        self.canonical_map[canonical] = canonical
                        
                        if aliases_str and "Kein Alias" not in aliases_str:
                            aliases = [a.strip() for a in aliases_str.split(",") if a.strip()]
                            for alias in aliases:
                                clean_alias = alias.replace("`", "").lower().strip()
                                self.canonical_map[clean_alias] = canonical
            
            logger.info(f"EdgeRegistry loaded from {full_path}: {len(self.valid_types)} canonical types.")

        except Exception as e:
            logger.error(f"Failed to parse Edge Vocabulary at {full_path}: {e}")

    def resolve(self, edge_type: str) -> str:
        """Normalisiert Kanten-Typen via Registry oder loggt Unbekannte für Review."""
        if not edge_type: return "related_to"
        
        # Normalisierung (Kleinschreibung, Unterstriche)
        clean_type = edge_type.lower().strip().replace(" ", "_")
        
        # 1. Lookup in Map (Canonical oder Alias)
        if clean_type in self.canonical_map:
            return self.canonical_map[clean_type]
        
        # 2. Unknown Handling (Loggen aber nicht verwerfen - Learning System)
        self._log_unknown(clean_type)
        return clean_type 

    def _log_unknown(self, edge_type: str):
        """Schreibt unbekannte Typen für späteres Review in ein Log-File."""
        try:
            os.makedirs(os.path.dirname(self.unknown_log_path), exist_ok=True)
            entry = {"unknown_type": edge_type, "status": "new"}
            with open(self.unknown_log_path, "a", encoding="utf-8") as f:
                f.write(json.dumps(entry) + "\n")
        except Exception:
            pass 

# Globale Singleton Instanz
registry = EdgeRegistry()