pfad Auflösung
This commit is contained in:
parent
99482ad65a
commit
81d005d969
|
|
@ -1,3 +1,8 @@
|
||||||
|
"""
|
||||||
|
FILE: app/services/edge_registry.py
|
||||||
|
DESCRIPTION: Single Source of Truth für Kanten-Typen mit dynamischem Reload.
|
||||||
|
VERSION: 0.7.1 (Fix: Silent Path Error & Path Alignment)
|
||||||
|
"""
|
||||||
import re
|
import re
|
||||||
import os
|
import os
|
||||||
import json
|
import json
|
||||||
|
|
@ -11,7 +16,6 @@ logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
class EdgeRegistry:
|
class EdgeRegistry:
|
||||||
_instance = None
|
_instance = None
|
||||||
# System-Kanten, die NIEMALS manuell im Markdown stehen dürfen
|
|
||||||
FORBIDDEN_SYSTEM_EDGES = {"next", "prev", "belongs_to"}
|
FORBIDDEN_SYSTEM_EDGES = {"next", "prev", "belongs_to"}
|
||||||
|
|
||||||
def __new__(cls, *args, **kwargs):
|
def __new__(cls, *args, **kwargs):
|
||||||
|
|
@ -28,24 +32,37 @@ class EdgeRegistry:
|
||||||
env_vocab_path = os.getenv("MINDNET_VOCAB_PATH")
|
env_vocab_path = os.getenv("MINDNET_VOCAB_PATH")
|
||||||
env_vault_root = os.getenv("MINDNET_VAULT_ROOT") or getattr(settings, "MINDNET_VAULT_ROOT", "./vault")
|
env_vault_root = os.getenv("MINDNET_VAULT_ROOT") or getattr(settings, "MINDNET_VAULT_ROOT", "./vault")
|
||||||
|
|
||||||
|
# WP-22 FIX: Pfad-Priorität angepasst auf _system/dictionary (Architektur-Standard)
|
||||||
if env_vocab_path:
|
if env_vocab_path:
|
||||||
self.full_vocab_path = os.path.abspath(env_vocab_path)
|
self.full_vocab_path = os.path.abspath(env_vocab_path)
|
||||||
else:
|
else:
|
||||||
self.full_vocab_path = os.path.abspath(
|
# Suche an zwei Orten: Erst System-Dir, dann User-Manual
|
||||||
|
possible_paths = [
|
||||||
|
os.path.join(env_vault_root, "_system", "dictionary", "edge_vocabulary.md"),
|
||||||
os.path.join(env_vault_root, "01_User_Manual", "01_edge_vocabulary.md")
|
os.path.join(env_vault_root, "01_User_Manual", "01_edge_vocabulary.md")
|
||||||
)
|
]
|
||||||
|
self.full_vocab_path = None
|
||||||
|
for p in possible_paths:
|
||||||
|
if os.path.exists(p):
|
||||||
|
self.full_vocab_path = os.path.abspath(p)
|
||||||
|
break
|
||||||
|
|
||||||
|
if not self.full_vocab_path:
|
||||||
|
self.full_vocab_path = os.path.abspath(possible_paths[0]) # Fallback
|
||||||
|
|
||||||
self.unknown_log_path = "data/logs/unknown_edges.jsonl"
|
self.unknown_log_path = "data/logs/unknown_edges.jsonl"
|
||||||
self.canonical_map: Dict[str, str] = {}
|
self.canonical_map: Dict[str, str] = {}
|
||||||
self.valid_types: Set[str] = set()
|
self.valid_types: Set[str] = set()
|
||||||
self._last_mtime = 0.0 # Für dynamisches Neuladen
|
self._last_mtime = 0.0
|
||||||
|
|
||||||
self.ensure_latest()
|
self.ensure_latest()
|
||||||
self.initialized = True
|
self.initialized = True
|
||||||
|
|
||||||
def ensure_latest(self):
|
def ensure_latest(self):
|
||||||
"""Prüft den Zeitstempel der Datei und lädt ggf. neu."""
|
"""Prüft den Zeitstempel und meldet Fehler nun explizit."""
|
||||||
if not os.path.exists(self.full_vocab_path):
|
if not os.path.exists(self.full_vocab_path):
|
||||||
|
# WP-22 FIX: Fehlermeldung statt silent return
|
||||||
|
logger.error(f"❌ EdgeRegistry: Vocabulary file NOT FOUND at {self.full_vocab_path}")
|
||||||
return
|
return
|
||||||
|
|
||||||
current_mtime = os.path.getmtime(self.full_vocab_path)
|
current_mtime = os.path.getmtime(self.full_vocab_path)
|
||||||
|
|
@ -54,14 +71,16 @@ class EdgeRegistry:
|
||||||
self._last_mtime = current_mtime
|
self._last_mtime = current_mtime
|
||||||
|
|
||||||
def _load_vocabulary(self):
|
def _load_vocabulary(self):
|
||||||
"""Parst das Wörterbuch und baut die Canonical-Map auf."""
|
"""Parst das Wörterbuch mit verbessertem Logging."""
|
||||||
self.canonical_map.clear()
|
self.canonical_map.clear()
|
||||||
self.valid_types.clear()
|
self.valid_types.clear()
|
||||||
|
|
||||||
|
# Regex deckt **typ** und **`typ`** ab
|
||||||
pattern = re.compile(r"\|\s*\*\*`?([a-zA-Z0-9_-]+)`?\*\*\s*\|\s*([^|]+)\|")
|
pattern = re.compile(r"\|\s*\*\*`?([a-zA-Z0-9_-]+)`?\*\*\s*\|\s*([^|]+)\|")
|
||||||
|
|
||||||
try:
|
try:
|
||||||
with open(self.full_vocab_path, "r", encoding="utf-8") as f:
|
with open(self.full_vocab_path, "r", encoding="utf-8") as f:
|
||||||
|
c_types, c_aliases = 0, 0
|
||||||
for line in f:
|
for line in f:
|
||||||
match = pattern.search(line)
|
match = pattern.search(line)
|
||||||
if match:
|
if match:
|
||||||
|
|
@ -70,47 +89,40 @@ class EdgeRegistry:
|
||||||
|
|
||||||
self.valid_types.add(canonical)
|
self.valid_types.add(canonical)
|
||||||
self.canonical_map[canonical] = canonical
|
self.canonical_map[canonical] = canonical
|
||||||
|
c_types += 1
|
||||||
|
|
||||||
if aliases_str and "Kein Alias" not in aliases_str:
|
if aliases_str and "Kein Alias" not in aliases_str:
|
||||||
aliases = [a.strip() for a in aliases_str.split(",") if a.strip()]
|
aliases = [a.strip() for a in aliases_str.split(",") if a.strip()]
|
||||||
for alias in aliases:
|
for alias in aliases:
|
||||||
clean_alias = alias.replace("`", "").lower().strip().replace(" ", "_")
|
clean_alias = alias.replace("`", "").lower().strip().replace(" ", "_")
|
||||||
self.canonical_map[clean_alias] = canonical
|
self.canonical_map[clean_alias] = canonical
|
||||||
logger.info(f"EdgeRegistry reloaded: {len(self.valid_types)} types.")
|
c_aliases += 1
|
||||||
|
|
||||||
|
logger.info(f"✅ EdgeRegistry reloaded: {c_types} types and {c_aliases} aliases from {self.full_vocab_path}")
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.error(f"Error reading vocabulary: {e}")
|
logger.error(f"❌ EdgeRegistry: Error reading vocabulary: {e}")
|
||||||
|
|
||||||
def resolve(self, edge_type: str, provenance: str = "explicit", context: dict = None) -> str:
|
def resolve(self, edge_type: str, provenance: str = "explicit", context: dict = None) -> str:
|
||||||
"""
|
|
||||||
Validiert Kanten gegen System-Regeln und Wörterbuch.
|
|
||||||
- provenance: 'explicit' (User/Markdown) oder 'structure' (System-Pipeline)
|
|
||||||
- context: {'file': str, 'line': int}
|
|
||||||
"""
|
|
||||||
self.ensure_latest()
|
self.ensure_latest()
|
||||||
if not edge_type: return "related_to"
|
if not edge_type: return "related_to"
|
||||||
|
|
||||||
clean_type = edge_type.lower().strip().replace(" ", "_").replace("-", "_")
|
clean_type = edge_type.lower().strip().replace(" ", "_").replace("-", "_")
|
||||||
ctx = context or {}
|
ctx = context or {}
|
||||||
|
|
||||||
# 1. Check auf "verbotene" manuelle Nutzung von Systemkanten
|
|
||||||
if provenance == "explicit" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
if provenance == "explicit" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
||||||
self._log_issue(clean_type, "forbidden_system_usage", ctx)
|
self._log_issue(clean_type, "forbidden_system_usage", ctx)
|
||||||
return "related_to" # Fallback, um System-Integrität zu schützen
|
return "related_to"
|
||||||
|
|
||||||
# 2. Stillschweigende Akzeptanz für echte System-Struktur
|
|
||||||
if provenance == "structure" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
if provenance == "structure" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
||||||
return clean_type
|
return clean_type
|
||||||
|
|
||||||
# 3. Mapping gegen das Wörterbuch
|
|
||||||
if clean_type in self.canonical_map:
|
if clean_type in self.canonical_map:
|
||||||
return self.canonical_map[clean_type]
|
return self.canonical_map[clean_type]
|
||||||
|
|
||||||
# 4. Unbekannte Kante loggen
|
|
||||||
self._log_issue(clean_type, "unknown_type", ctx)
|
self._log_issue(clean_type, "unknown_type", ctx)
|
||||||
return clean_type
|
return clean_type
|
||||||
|
|
||||||
def _log_issue(self, edge_type: str, error_kind: str, ctx: dict):
|
def _log_issue(self, edge_type: str, error_kind: str, ctx: dict):
|
||||||
"""Schreibt detaillierte Fehler mit Fundort."""
|
|
||||||
try:
|
try:
|
||||||
os.makedirs(os.path.dirname(self.unknown_log_path), exist_ok=True)
|
os.makedirs(os.path.dirname(self.unknown_log_path), exist_ok=True)
|
||||||
entry = {
|
entry = {
|
||||||
|
|
@ -118,7 +130,8 @@ class EdgeRegistry:
|
||||||
"edge_type": edge_type,
|
"edge_type": edge_type,
|
||||||
"error": error_kind,
|
"error": error_kind,
|
||||||
"file": ctx.get("file", "unknown"),
|
"file": ctx.get("file", "unknown"),
|
||||||
"line": ctx.get("line", "unknown")
|
"line": ctx.get("line", "unknown"),
|
||||||
|
"note_id": ctx.get("note_id", "unknown")
|
||||||
}
|
}
|
||||||
with open(self.unknown_log_path, "a", encoding="utf-8") as f:
|
with open(self.unknown_log_path, "a", encoding="utf-8") as f:
|
||||||
f.write(json.dumps(entry) + "\n")
|
f.write(json.dumps(entry) + "\n")
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user