Spaces:
Running
Running
Download src/file_processors.py from jonels1988/DocShopProE-Cloud: direct link, hf CLI and curl.
- Browser
- Download file 5.87 kB
-
https://huggingface.co/spaces/jonels1988/DocShopProE-Cloud/resolve/main/src/file_processors.py
- Command line
-
hf download hf://spaces/jonels1988/DocShopProE-Cloud/src/file_processors.py
-
curl -L -o file_processors.py https://huggingface.co/spaces/jonels1988/DocShopProE-Cloud/resolve/main/src/file_processors.py
5.87 kB
| import pandas as pd | |
| import numpy as np | |
| from datetime import datetime | |
| import re | |
| from typing import Tuple, Optional, Dict, Any | |
| import logging | |
| logger = logging.getLogger(__name__) | |
| def process_uploaded_files(open_invoices_file: str, payment_notification_file: str) -> Tuple[pd.DataFrame, pd.DataFrame]: | |
| """Process uploaded files and convert to canonical format""" | |
| open_invoices_df = pd.DataFrame() | |
| payment_notifications_df = pd.DataFrame() | |
| if open_invoices_file: | |
| open_invoices_df = process_open_invoices(open_invoices_file) | |
| if payment_notification_file: | |
| payment_notifications_df = process_payment_notification(payment_notification_file) | |
| return open_invoices_df, payment_notifications_df | |
| def process_open_invoices(file_path: str) -> pd.DataFrame: | |
| """Process Open Invoices file to canonical format""" | |
| try: | |
| # Read file | |
| if file_path.endswith('.xlsx'): | |
| df = pd.read_excel(file_path) | |
| else: | |
| df = pd.read_csv(file_path) | |
| # Drop empty rows | |
| df = df.dropna(how='all') | |
| # Create canonical format | |
| processed_data = [] | |
| for idx, row in df.iterrows(): | |
| # Handle potential missing columns | |
| row_dict = row.to_dict() | |
| record = { | |
| 'id': f"INV_{idx:06d}", | |
| 'document_type': str(row_dict.get('Transaction type', 'Invoice')), | |
| 'document_number': str(row_dict.get('Num', f"INV_{idx}")), | |
| 'reference_number': None, | |
| 'po_number': str(row_dict.get('P.O. Number', '')), | |
| 'invoice_date': parse_date(row_dict.get('Date')), | |
| 'due_date': parse_date(row_dict.get('Due date')), | |
| 'total_billed': parse_currency(row_dict.get('Amount', 0)), | |
| 'amount_outstanding': parse_currency(row_dict.get('Open balance', 0)), | |
| 'discount': 0.0, | |
| 'credit_advances_applied': 0.0, | |
| 'payment_amount': 0.0, | |
| 'ar_status': str(row_dict.get('A/R paid', 'Unpaid')), | |
| 'open_balance': parse_currency(row_dict.get('Open balance', 0)) | |
| } | |
| processed_data.append(record) | |
| return pd.DataFrame(processed_data) | |
| except Exception as e: | |
| logger.error(f"Error processing open invoices: {str(e)}") | |
| # Return empty dataframe with expected structure | |
| return pd.DataFrame(columns=[ | |
| 'id', 'document_type', 'document_number', 'reference_number', 'po_number', | |
| 'invoice_date', 'due_date', 'total_billed', 'amount_outstanding', | |
| 'discount', 'credit_advances_applied', 'payment_amount', 'ar_status', 'open_balance' | |
| ]) | |
| def process_payment_notification(file_path: str) -> pd.DataFrame: | |
| """Process Payment Notification file to canonical format""" | |
| try: | |
| # Read file | |
| if file_path.endswith('.xlsx'): | |
| df = pd.read_excel(file_path) | |
| else: | |
| df = pd.read_csv(file_path) | |
| # Drop empty rows | |
| df = df.dropna(how='all') | |
| # Create canonical format | |
| processed_data = [] | |
| for idx, row in df.iterrows(): | |
| # Handle potential missing columns | |
| row_dict = row.to_dict() | |
| record = { | |
| 'id': f"PAY_{idx:06d}", | |
| 'document_type': 'Payment', | |
| 'document_number': str(row_dict.get('Bill number', f"PAY_{idx}")), | |
| 'reference_number': str(row_dict.get('Reference', '')), | |
| 'po_number': None, | |
| 'invoice_date': parse_date(row_dict.get('Date')), | |
| 'due_date': None, | |
| 'total_billed': parse_currency(row_dict.get('Total billed', 0)), | |
| 'amount_outstanding': parse_currency(row_dict.get('Amount outstanding', 0)), | |
| 'discount': parse_currency(row_dict.get('Discount', 0)), | |
| 'credit_advances_applied': parse_currency(row_dict.get('Credit/advances applied', 0)), | |
| 'payment_amount': parse_currency(row_dict.get('Payment amount', 0)), | |
| 'ar_status': 'Paid', | |
| 'open_balance': parse_currency(row_dict.get('Amount outstanding', 0)) | |
| } | |
| processed_data.append(record) | |
| return pd.DataFrame(processed_data) | |
| except Exception as e: | |
| logger.error(f"Error processing payment notification: {str(e)}") | |
| # Return empty dataframe with expected structure | |
| return pd.DataFrame(columns=[ | |
| 'id', 'document_type', 'document_number', 'reference_number', 'po_number', | |
| 'invoice_date', 'due_date', 'total_billed', 'amount_outstanding', | |
| 'discount', 'credit_advances_applied', 'payment_amount', 'ar_status', 'open_balance' | |
| ]) | |
| def parse_date(date_value) -> Optional[datetime]: | |
| """Parse various date formats to datetime""" | |
| if pd.isna(date_value) or date_value == '' or date_value is None: | |
| return datetime.now() # Default to current date | |
| try: | |
| parsed = pd.to_datetime(date_value, errors='coerce') | |
| if pd.isna(parsed): | |
| return datetime.now() | |
| return parsed | |
| except: | |
| return datetime.now() | |
| def parse_currency(currency_value) -> float: | |
| """Parse currency values to float""" | |
| if pd.isna(currency_value) or currency_value is None: | |
| return 0.0 | |
| try: | |
| if isinstance(currency_value, (int, float)): | |
| return float(currency_value) | |
| # Remove currency symbols and commas | |
| cleaned = str(currency_value).replace('$', '').replace(',', '').replace(' ', '').strip() | |
| if cleaned == '': | |
| return 0.0 | |
| return float(cleaned) | |
| except: | |
| return 0.0 |