Initial

core/data_processor.py

@@ -0,0 +1,67 @@
+import pandas as pd
+import requests
+from io import StringIO
+from datetime import datetime, timedelta
+from .config_loader import config
+
+_cache = {"events": None, "remarks": None}
+HEADERS = {"User-Agent": "Mozilla/5.0"}
+
+def invalidate_cache():
+    global _cache
+    _cache = {"events": None, "remarks": None}
+    print("DEBUG: Cache wurde manuell geleert.")
+    return "Cache gelöscht"
+
+def get_upcoming_events():
+    if _cache["events"] is not None:
+        return _cache["events"]
+    
+    url = config['links']['times_csv']
+    print(f"DEBUG: Lade Zeiten von URL: {url}")
+    
+    response = requests.get(url, headers=HEADERS)
+    df = pd.read_csv(StringIO(response.text))
+    
+    # Debug: Spaltennamen prüfen
+    print(f"DEBUG: Spalten in Zeiten-Sheet gefunden: {df.columns.tolist()}")
+
+    date_col = config['google_sheet']['date_column']
+    df = df.dropna(subset=[date_col])
+    df[date_col] = pd.to_datetime(df[date_col], dayfirst=True, errors='coerce')
+    df = df.dropna(subset=[date_col]).fillna('')
+    
+    heute = pd.Timestamp(datetime.now().date())
+    ende = heute + timedelta(days=config['processing']['days_to_show'])
+    
+    mask = (df[date_col] >= heute) & (df[date_col] <= ende)
+    gefilterte = df.loc[mask].sort_values(by=date_col).copy()
+    
+    wt_map = {0: 'Mo', 1: 'Di', 2: 'Mi', 3: 'Do', 4: 'Fr', 5: 'Sa', 6: 'So'}
+    gefilterte['Wochentag'] = gefilterte[date_col].dt.weekday.map(wt_map)
+    
+    _cache["events"] = gefilterte.to_dict(orient='records')
+    return _cache["events"]
+
+def get_remarks():
+    if _cache["remarks"] is not None:
+        return _cache["remarks"]
+    
+    url = config['links']['remarks_csv']
+    print(f"DEBUG: Lade Bemerkungen von URL: {url}")
+    
+    response = requests.get(url, headers=HEADERS)
+    
+    # Debug: Die ersten 100 Zeichen der Antwort sehen
+    print(f"DEBUG: Raw Data Bemerkungen (Anfang): {response.text[:100]}...")
+    
+    df = pd.read_csv(StringIO(response.text), skiprows=2, header=None)
+    
+    if not df.empty:
+        print(f"DEBUG: Bemerkungen-DF Head:\n{df.head(3)}")
+        remarks = df[0].dropna().astype(str).tolist()
+        _cache["remarks"] = [r.strip() for r in remarks if r.strip()]
+    else:
+        _cache["remarks"] = []
+        
+    return _cache["remarks"]