InfoLeaseExtract/ManualInvoice.py

import os
import pandas as pd
from datetime import datetime as dt, timedelta
import re
from pathlib import Path
import time
import numpy as np
from pprint import pprint as prt


def pfd(df: pd.DataFrame):
    with pd.option_context('display.max_rows', None, 'display.max_columns', None):  # more options can be specified also
        print(df)


def create_line_divider(breakage_list: list):
    """
    This allows for the creation of a custom data extractor
    Breakage list defines the split points that will be used for the line
    Example
    Given breakage_list [10, 20, 30]
    using slot_num 0 in the resulting extract_line_slot will yield
    characters 0 - 10 from the string. 
    Slot 1 would give characters 10 - 20
    """
    def extract_line_slot(slot_num : int, line_string: str, debug : bool = False):
        """
        Pulls data from a line/string using break points defined by the
        parent function.
        ONLY USE THIS FUNCTION THROUGH CREATION USING 'create_line_extractor'
        Will automatically convert numbers to floats
        """
        # We can't have a slot number higher than the number of slots
        assert(slot_num < len(breakage_list)+1)
        low_range = 0 if slot_num == 0 else breakage_list[slot_num-1]
        high_range = len(line_string) if slot_num == len(breakage_list) else breakage_list[slot_num]
        # In order to create a float we need to remove the , from the string
        data = line_string[low_range:high_range].strip().replace(",", "")
        try: data = float(data)
        except: pass
        if debug:
            print(f"Slot num: {slot_num} | Low: {low_range} | High: {high_range} | Data: {data}")
        return data
    return extract_line_slot


def minv(report: str, save_name: str):
    lines = report.splitlines()
    data_extractor = create_line_divider([15,32,52,71,83,107,116,128])
    extracted_data_dict = {
        "ContractNumber" : [],
        "UTAB_OIC_DUE" : [],
        "RentalDue" : [],
        "UTAB_OIC_PYMT" : [],
        "ChargeType" : [],
        "OutstandBalance" : [],
        "BizSegment" : [],
        "BookingDate" : [],
        "Branch" : [],
    }
    columns = list(extracted_data_dict.keys())
    for line in enumerate(lines):
        if re.search(contract_number_regex, line[1]) != None:
            [extracted_data_dict[columns[c]].append(data_extractor(c,line[1],debug=False)) for c in range(0,len(columns))]
    #All the list lengths need to be the same so if anything was missed it will fail to build
    dataframe = pd.DataFrame(extracted_data_dict)
    # ( bookdate != today & rent = 0 ) OR (outstanding > 100 & rent = 0)
    # dt.today().strftime("%m/%m/%Y")
    filtered = dataframe[
        ((dataframe["BookingDate"] != '04/26/2022') & (dataframe["RentalDue"] == 0)) |\
        ((dataframe["RentalDue"] == 0 )             & (dataframe["OutstandBalance"] > 100))]
    filtered.to_excel(save_name, index=False)
    return filtered

current_output = [
    '100-1011756-004',
    '100-1354567-002',
    '100-1637209-005',
    '100-1665517-003',
    '100-1670517-003',
    '100-2081987-008',
    '100-2139037-002',
    '100-2446458-002',
    '100-2453558-003',
    '100-2611389-007',
    '100-3492758-003',
    '100-3500858-001',
    '100-3694757-001',
    '100-3725849-003',
    '100-3876959-007',
    '100-3910629-001',
    '100-3964329-001',
    '100-4462739-001',
    '100-4850431-001',
    '100-4945021-001',
    '100-5382471-001',
    '100-6738611-001',
    '100-6849836-001',
    '100-7037791-001',
    '100-7045691-001',
    '100-7052571-001',
    '100-7059671-001',
    '100-7087121-001',
    '100-7107941-001',
    '100-7146771-001',
    '100-7156851-001',
    '100-7178461-001',
    '100-7203371-001',
    '100-7219911-001',
    '100-7232561-001',
    '100-7237601-001',
    '100-7242461-001',
    '100-9660710-001',
    '100-9723689-001',
]

contract_number_regex = "\d{3}-\d{7}-\d{3}"

with open("2022.05.04_MINV_C", errors="replace") as ifile:
    report = ifile.read()

fin_df = minv(report, "man_inv_test.xlsx")
pfd(fin_df)
il_contracts = fin_df.ContractNumber.to_list()
prt(il_contracts) 

extra_contracts = []
not_included = []
for c in il_contracts:
    if c not in current_output:
        extra_contracts.append(c)
for c in current_output:
    if c not in il_contracts:
        not_included.append(c)

print("\nExtra Contracts:")
prt(extra_contracts)
print("Not Included Contracts:")
prt(not_included)
print(f"MATCHING CONTRACTS: {il_contracts == current_output}")
print(f"Current # contract {len(current_output)} | ILE Processed Contracts: {len(il_contracts)}")
print(f"# Extra contracts included: {len(extra_contracts)} | # Contracts not included: {len(not_included)}")