Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sync_manager.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-08-28 08:22:20 +00:00
parent fddd0311d7
commit 35b491633e
1 changed files with 18 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
sync_manager.py
View File

@@ -46,14 +46,21 @@ class SyncManager:
"""Lädt und bereitet die Daten aus D365 und Google Sheets vor.""" """Lädt und bereitet die Daten aus D365 und Google Sheets vor."""
self.logger.info(f"Lade Daten aus D365-Export: '{self.d365_export_path}'...") self.logger.info(f"Lade Daten aus D365-Export: '{self.d365_export_path}'...")
try: try:
self.d365_df = pd.read_excel(self.d365_export_path, dtype=str).fillna('') temp_d365_df = pd.read_excel(self.d365_export_path, dtype=str).fillna('')
d365_guid_col = next((k for k, v in self.d365_to_gsheet_map.items() if v == "CRM ID"), None)
if d365_guid_col and d365_guid_col in self.d365_df.columns: # --- FINALE, ROBUSTE LOGIK ---
self.d365_df.rename(columns={d365_guid_col: "CRM ID"}, inplace=True) # 1. Prüfen, ob alle benötigten Original-Spalten vorhanden sind
else: for d365_col in self.d365_to_gsheet_map.keys():
raise ValueError(f"GUID-Spalte ('{d365_guid_col}') nicht in D365-Export gefunden.") if d365_col not in temp_d365_df.columns:
raise ValueError(f"Erwartete Spalte '{d365_col}' nicht in der D365-Exportdatei gefunden.")
# 2. Erstelle ein neues, sauberes DataFrame, das nur die Spalten enthält, die wir brauchen
self.d365_df = temp_d365_df[list(self.d365_to_gsheet_map.keys())].copy()
# 3. Benenne die Spalten im neuen DataFrame um
self.d365_df.rename(columns=self.d365_to_gsheet_map, inplace=True)
# 4. Bereinige die GUIDs
self.d365_df['CRM ID'] = self.d365_df['CRM ID'].str.strip().str.lower() self.d365_df['CRM ID'] = self.d365_df['CRM ID'].str.strip().str.lower()
self.d365_df = self.d365_df[self.d365_df['CRM ID'].str.match(r'^[0-9a-f]{8}-([0-9a-f]{4}-){3}[0-9a-f]{12}$', na=False)] self.d365_df = self.d365_df[self.d365_df['CRM ID'].str.match(r'^[0-9a-f]{8}-([0-9a-f]{4}-){3}[0-9a-f]{12}$', na=False)]
@@ -74,9 +81,8 @@ class SyncManager:
if temp_df.empty: if temp_df.empty:
temp_df = pd.DataFrame(columns=actual_header) temp_df = pd.DataFrame(columns=actual_header)
else: else:
if temp_df.shape[1] < len(actual_header): if temp_df.shape[1] > len(actual_header):
missing_cols = len(actual_header) - temp_df.shape[1] temp_df = temp_df.iloc[:, :len(actual_header)]
for i in range(missing_cols): temp_df[f'temp_{i}'] = ''
temp_df.columns = actual_header temp_df.columns = actual_header
temp_df = temp_df.fillna('') temp_df = temp_df.fillna('')
@@ -92,11 +98,11 @@ class SyncManager:
self.gsheet_df['CRM ID'] = self.gsheet_df['CRM ID'].str.strip().str.lower() self.gsheet_df['CRM ID'] = self.gsheet_df['CRM ID'].str.strip().str.lower()
# --- FINALE BEREINIGUNG: Nur echte GUIDs im GSheet DataFrame behalten ---
initial_row_count = len(self.gsheet_df) initial_row_count = len(self.gsheet_df)
self.gsheet_df = self.gsheet_df[self.gsheet_df['CRM ID'].str.match(r'^[0-9a-f]{8}-([0-9a-f]{4}-){3}[0-9a-f]{12}$', na=False)] self.gsheet_df = self.gsheet_df[self.gsheet_df['CRM ID'].str.match(r'^[0-9a-f]{8}-([0-9a-f]{4}-){3}[0-9a-f]{12}$', na=False)]
final_row_count = len(self.gsheet_df) final_row_count = len(self.gsheet_df)
self.logger.info(f"GSheet-Daten bereinigt: {initial_row_count - final_row_count} Zeilen ohne gültige GUID entfernt.") if initial_row_count > final_row_count:
self.logger.info(f"GSheet-Daten bereinigt: {initial_row_count - final_row_count} Zeilen ohne gültige GUID entfernt.")
self.logger.info(f"{len(self.d365_df)} gültige Datensätze aus D365 geladen, {len(self.gsheet_df)} gültige Datensätze im Google Sheet.") self.logger.info(f"{len(self.d365_df)} gültige Datensätze aus D365 geladen, {len(self.gsheet_df)} gültige Datensätze im Google Sheet.")
return True return True