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 12:48:10 +00:00
parent 38e7614d34
commit b108ebc0be
1 changed files with 22 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
sync_manager.py
View File

@@ -36,10 +36,14 @@ class SyncManager:
"Number of Employees": "CRM Anzahl Mitarbeiter", "Number of Employees": "CRM Anzahl Mitarbeiter",
"GUID": "CRM ID" "GUID": "CRM ID"
} }
# --- ANGEPASSTE LOGIK-LISTEN ---
# Spalten, bei denen D365 (fast) immer gewinnt
self.d365_wins_cols = ["CRM Name", "Parent Account Name", "CRM Ort", "CRM Land", self.d365_wins_cols = ["CRM Name", "Parent Account Name", "CRM Ort", "CRM Land",
"CRM Beschreibung", "CRM Branche", "CRM Anzahl Techniker", "CRM Anzahl Techniker", "CRM Branche", "CRM Umsatz",
"CRM Umsatz", "CRM Anzahl Mitarbeiter"] "CRM Anzahl Mitarbeiter", "CRM Beschreibung"]
# Spalten, bei denen unsere angereicherten Daten im GSheet Vorrang haben
self.smart_merge_cols = ["CRM Website"] self.smart_merge_cols = ["CRM Website"]
def _load_data(self): def _load_data(self):
@@ -48,19 +52,12 @@ class SyncManager:
try: try:
temp_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('')
# --- FINALE, ROBUSTE LOGIK ---
# 1. Prüfen, ob alle benötigten Original-Spalten vorhanden sind
for d365_col in self.d365_to_gsheet_map.keys(): for d365_col in self.d365_to_gsheet_map.keys():
if d365_col not in temp_d365_df.columns: if d365_col not in temp_d365_df.columns:
raise ValueError(f"Erwartete Spalte '{d365_col}' nicht in der D365-Exportdatei gefunden.") 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() 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) 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)]
@@ -76,33 +73,29 @@ class SyncManager:
else: else:
actual_header = all_data_with_headers[self.sheet_handler._header_rows - 1] actual_header = all_data_with_headers[self.sheet_handler._header_rows - 1]
data_rows = all_data_with_headers[self.sheet_handler._header_rows:] data_rows = all_data_with_headers[self.sheet_handler._header_rows:]
temp_df = pd.DataFrame(data_rows) temp_df = pd.DataFrame(data_rows)
if temp_df.empty:
temp_df = pd.DataFrame(columns=actual_header) if not temp_df.empty:
else:
if temp_df.shape[1] > len(actual_header): if temp_df.shape[1] > len(actual_header):
temp_df = temp_df.iloc[:, :len(actual_header)] temp_df = temp_df.iloc[:, :len(actual_header)]
temp_df.columns = actual_header temp_df.columns = actual_header
else:
temp_df = pd.DataFrame(columns=actual_header)
temp_df = temp_df.fillna('') temp_df = temp_df.fillna('')
for col_name in COLUMN_ORDER: for col_name in COLUMN_ORDER:
if col_name not in temp_df.columns: if col_name not in temp_df.columns:
temp_df[col_name] = '' temp_df[col_name] = ''
self.gsheet_df = temp_df[COLUMN_ORDER] self.gsheet_df = temp_df[COLUMN_ORDER]
except Exception as e: except Exception as e:
self.logger.critical(f"Fehler beim Laden/Umwandeln der GSheet-Daten: {e}", exc_info=True) self.logger.critical(f"Fehler beim Laden/Umwandeln der GSheet-Daten: {e}", exc_info=True)
return False return False
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()
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) if initial_row_count > len(self.gsheet_df):
if initial_row_count > final_row_count: self.logger.info(f"GSheet-Daten bereinigt: {initial_row_count - len(self.gsheet_df)} Zeilen ohne gültige GUID entfernt.")
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
@@ -117,7 +110,7 @@ class SyncManager:
return return
d365_ids = set(self.d365_df['CRM ID'].dropna()) d365_ids = set(self.d365_df['CRM ID'].dropna())
gsheet_ids = set(self.gsheet_df[self.gsheet_df['CRM ID'] != '']['CRM ID'].dropna()) gsheet_ids = set(self.gsheet_df['CRM ID'].dropna())
new_ids = d365_ids - gsheet_ids new_ids = d365_ids - gsheet_ids
deleted_ids = set() deleted_ids = set()
@@ -163,11 +156,8 @@ class SyncManager:
trigger_update = True trigger_update = True
elif gsheet_col == 'CRM Anzahl Techniker': elif gsheet_col == 'CRM Anzahl Techniker':
# NEUE, ERWEITERTE REGEL if (d365_val == '-1' or d365_val == '0') and gsheet_val == '': pass
if (d365_val == '-1' or d365_val == '0') and gsheet_val == '': elif d365_val != gsheet_val: trigger_update = True
pass # Behandle '-1' und '0' als identisch zu leer
elif d365_val != gsheet_val:
trigger_update = True
elif gsheet_col == 'CRM Branche': elif gsheet_col == 'CRM Branche':
if gsheet_row['Chat Vorschlag Branche'] == '' and d365_val != gsheet_val: if gsheet_row['Chat Vorschlag Branche'] == '' and d365_val != gsheet_val:
@@ -180,8 +170,12 @@ class SyncManager:
elif gsheet_col == 'CRM Anzahl Mitarbeiter': elif gsheet_col == 'CRM Anzahl Mitarbeiter':
if gsheet_row['Wiki Mitarbeiter'] == '' and d365_val != gsheet_val: if gsheet_row['Wiki Mitarbeiter'] == '' and d365_val != gsheet_val:
trigger_update = True trigger_update = True
else: elif gsheet_col == 'CRM Beschreibung':
if gsheet_row['Website Zusammenfassung'] == '' and d365_val != gsheet_val:
trigger_update = True
else: # Gilt nur noch für Name, Ort, Parent
if d365_val != gsheet_val: if d365_val != gsheet_val:
trigger_update = True trigger_update = True
@@ -193,7 +187,6 @@ class SyncManager:
for gsheet_col in self.smart_merge_cols: for gsheet_col in self.smart_merge_cols:
d365_val = str(d365_row.get(gsheet_col, '')).strip() d365_val = str(d365_row.get(gsheet_col, '')).strip()
gsheet_val = str(gsheet_row.get(gsheet_col, '')).strip() gsheet_val = str(gsheet_row.get(gsheet_col, '')).strip()
if d365_val and not gsheet_val: if d365_val and not gsheet_val:
row_updates[gsheet_col] = d365_val row_updates[gsheet_col] = d365_val
needs_reeval = True needs_reeval = True