neue parser logik
This commit is contained in:
1 parent
2d43e0596c
commit
99482ad65a
3 files changed
+107
-48
No files matched your search
@@ -1,16 +1,9 @@
|
||||
"""
|
||||
FILE: app/services/edge_registry.py
|
||||
DESCRIPTION: Single Source of Truth für Kanten-Typen.
|
||||
FIX: Regex angepasst auf Format **`canonical`** (Bold + Backticks).
|
||||
VERSION: 0.6.10 (Regex Precision Update)
|
||||
"""
|
||||
import re
|
||||
import os
|
||||
import json
|
||||
import logging
|
||||
from typing import Dict, Optional, Set
|
||||
|
||||
print(">>> MODULE_LOAD: edge_registry.py initialized <<<", flush=True)
|
||||
import time
|
||||
from typing import Dict, Optional, Set, Tuple
|
||||
|
||||
from app.config import get_settings
|
||||
|
||||
@@ -18,6 +11,8 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
class EdgeRegistry:
|
||||
_instance = None
|
||||
# System-Kanten, die NIEMALS manuell im Markdown stehen dürfen
|
||||
FORBIDDEN_SYSTEM_EDGES = {"next", "prev", "belongs_to"}
|
||||
|
||||
def __new__(cls, *args, **kwargs):
|
||||
if cls._instance is None:
|
||||
@@ -43,26 +38,30 @@ class EdgeRegistry:
|
||||
self.unknown_log_path = "data/logs/unknown_edges.jsonl"
|
||||
self.canonical_map: Dict[str, str] = {}
|
||||
self.valid_types: Set[str] = set()
|
||||
self._last_mtime = 0.0 # Für dynamisches Neuladen
|
||||
|
||||
self._load_vocabulary()
|
||||
self.ensure_latest()
|
||||
self.initialized = True
|
||||
|
||||
def _load_vocabulary(self):
|
||||
"""Parst die Markdown-Tabelle im Vault."""
|
||||
print(f">>> CHECK: Loading Vocabulary from {self.full_vocab_path}", flush=True)
|
||||
|
||||
def ensure_latest(self):
|
||||
"""Prüft den Zeitstempel der Datei und lädt ggf. neu."""
|
||||
if not os.path.exists(self.full_vocab_path):
|
||||
print(f"!!! [DICT-ERROR] File not found: {self.full_vocab_path} !!!", flush=True)
|
||||
return
|
||||
|
||||
# WP-22 Precision Regex:
|
||||
# Sucht nach | **`typ`** | oder | **typ** |
|
||||
# Die Backticks `? sind jetzt optional enthalten.
|
||||
current_mtime = os.path.getmtime(self.full_vocab_path)
|
||||
if current_mtime > self._last_mtime:
|
||||
self._load_vocabulary()
|
||||
self._last_mtime = current_mtime
|
||||
|
||||
def _load_vocabulary(self):
|
||||
"""Parst das Wörterbuch und baut die Canonical-Map auf."""
|
||||
self.canonical_map.clear()
|
||||
self.valid_types.clear()
|
||||
|
||||
pattern = re.compile(r"\|\s*\*\*`?([a-zA-Z0-9_-]+)`?\*\*\s*\|\s*([^|]+)\|")
|
||||
|
||||
try:
|
||||
with open(self.full_vocab_path, "r", encoding="utf-8") as f:
|
||||
c_types, c_aliases = 0, 0
|
||||
for line in f:
|
||||
match = pattern.search(line)
|
||||
if match:
|
||||
@@ -71,39 +70,56 @@ class EdgeRegistry:
|
||||
|
||||
self.valid_types.add(canonical)
|
||||
self.canonical_map[canonical] = canonical
|
||||
c_types += 1
|
||||
|
||||
if aliases_str and "Kein Alias" not in aliases_str:
|
||||
# Aliase säubern (entfernt Backticks auch hier)
|
||||
aliases = [a.strip() for a in aliases_str.split(",") if a.strip()]
|
||||
for alias in aliases:
|
||||
clean_alias = alias.replace("`", "").lower().strip().replace(" ", "_")
|
||||
self.canonical_map[clean_alias] = canonical
|
||||
c_aliases += 1
|
||||
|
||||
if c_types == 0:
|
||||
print("!!! [DICT-WARN] Pattern mismatch! Ensure types are **`canonical`** or **canonical**. !!!", flush=True)
|
||||
else:
|
||||
print(f"=== [DICT-SUCCESS] Registered {c_types} Canonical Types and {c_aliases} Aliases ===", flush=True)
|
||||
|
||||
logger.info(f"EdgeRegistry reloaded: {len(self.valid_types)} types.")
|
||||
except Exception as e:
|
||||
print(f"!!! [DICT-FATAL] Error reading file: {e} !!!", flush=True)
|
||||
logger.error(f"Error reading vocabulary: {e}")
|
||||
|
||||
def resolve(self, edge_type: str) -> str:
|
||||
"""Normalisiert Kanten-Typen via Registry oder loggt Unbekannte."""
|
||||
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()
|
||||
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 {}
|
||||
|
||||
# 1. Check auf "verbotene" manuelle Nutzung von Systemkanten
|
||||
if provenance == "explicit" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
||||
self._log_issue(clean_type, "forbidden_system_usage", ctx)
|
||||
return "related_to" # Fallback, um System-Integrität zu schützen
|
||||
|
||||
# 2. Stillschweigende Akzeptanz für echte System-Struktur
|
||||
if provenance == "structure" and clean_type in self.FORBIDDEN_SYSTEM_EDGES:
|
||||
return clean_type
|
||||
|
||||
# 3. Mapping gegen das Wörterbuch
|
||||
if clean_type in self.canonical_map:
|
||||
return self.canonical_map[clean_type]
|
||||
|
||||
self._log_unknown(clean_type)
|
||||
# 4. Unbekannte Kante loggen
|
||||
self._log_issue(clean_type, "unknown_type", ctx)
|
||||
return clean_type
|
||||
|
||||
def _log_unknown(self, edge_type: str):
|
||||
def _log_issue(self, edge_type: str, error_kind: str, ctx: dict):
|
||||
"""Schreibt detaillierte Fehler mit Fundort."""
|
||||
try:
|
||||
os.makedirs(os.path.dirname(self.unknown_log_path), exist_ok=True)
|
||||
entry = {"unknown_type": edge_type, "status": "new"}
|
||||
entry = {
|
||||
"timestamp": time.strftime("%Y-%m-%d %H:%M:%S"),
|
||||
"edge_type": edge_type,
|
||||
"error": error_kind,
|
||||
"file": ctx.get("file", "unknown"),
|
||||
"line": ctx.get("line", "unknown")
|
||||
}
|
||||
with open(self.unknown_log_path, "a", encoding="utf-8") as f:
|
||||
f.write(json.dumps(entry) + "\n")
|
||||
except Exception: pass
|
||||
|
||||
Reference in new issue
Block a user