cleaned up main, added comments to ILextract

ILExtract.py

@@ -5,45 +5,33 @@ import sys, getopt
 import re
 from pathlib import Path
 import time
+import numpy as np
 
+# contract numbers are a common feature in many reports to it's
+# useful to have the regex for them globally avaiable
 contract_number_regex = "\d{3}-\d{7}-\d{3}"
 
-
 class ILReport:
     """
     InfoLease Report class will be used to work with the files.
     It makes it easier to add new reports to the workflow and to make it more clear where
     the reports are coming from. It also helps with tracking reports that may not be ready yet.
     """
-    def __init__(self, location, extraction_function = None, output_location = None, output_name = None):
+    def __init__(self, location, extraction_function, output_location = None):
         # The location where the InfoLease report is stored
         self.location = location
-        # The base name of the file, corresponds to the report type
         # If output location not specified, save to the input location
         if output_location == None:
             self.output_location = Path(location).parent.absolute()
         else: 
-            self.output_location = output_location
+            self.output_location = output_location    
-        # This is optional but has a default
-        if output_name == None:
-            # Get the file name of the input and remove the date
-            self.output_name = os.path.basename(f"{self.location}")\
-                .replace(f"{(dt.now() - timedelta(days=+1)).strftime('%Y.%m.%d')}","")
-        else:
-            self.output_name = output_name
         # The function used to extract the data from the report
         self.x_method = extraction_function
         # Tracks whether the data was successfully exctracted
         self.successful  = False
         
-        
+
-    def run(self) -> int:
+    def process(self):
-        """
-        This method is what actully run the report. I uses the specidied extraction function to create and save an excel document.
-        SUCESS returns 0
-        ERROR returns 1
-        Failure is also noted by self.success == False
-        """
         try:
             # Open the file and read it to a string | errors = 'replace' deals with non UTF-8 characters (no affect on output)
             with open(self.location, errors="replace") as ifile:
@@ -55,48 +43,16 @@ class ILReport:
         try: 
             # Run the associated method to extract the data and get the dataframe
             dataframe = self.x_method(report, self.output_location)
-            try:
-                assert(len(dataframe) > 1)
-            except Exception as e:
-                print(f"Data Length Error: {self.output_name} is empty:\n{dataframe}")
-                self.successful = False
-                return 1
         except Exception as e:
-            print(f"{self.output_name} failed to process:\n{e}")
+            print(f"Failed to create dataframe: {self.output_name}\n{e}")
-            self.successful = False
-            return 1
-        try:
-            # Save the dataframe as an excel document
-            dataframe.to_excel(self.output_location, index = False, engine="openpyxl")
-        except Exception as e:
-            self.successful = False
-            print(f"{self.output_location} failed to save to excel!\n{dataframe}\n{e}")
-            return 1
-        self.successful = True
-        return dataframe
-
-    def process(self):
-        try:
-            # Open the file and read it to a string | errors = 'replace' deals with non UTF-8 characters (no affect on output)
-            with open(self.location, errors="replace") as ifile:
-                report = ifile.read()
-        except IOError as ioe:
-            print(f"Failed to open file: {self.location}\n{ioe}")
             self.successful = False
             return 1
-        #try: 
-            # Run the associated method to extract the data and get the dataframe
-        dataframe = self.x_method(report, self.output_location)
         try:
             assert(len(dataframe) > 1)
         except Exception as e:
             print(f"Data Length Error: {self.output_name} is empty:\n{dataframe}")
             self.successful = False
             return 1
-        #except Exception as e:
-        #    print(f"{self.output_name} failed to process:\n{e}")
-        #    self.successful = False
-        #    return 1
         return dataframe
    
 
@@ -117,9 +73,11 @@ def create_line_divider(breakage_list: list):
         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
@@ -188,21 +146,36 @@ def ach(report: str, save_name: str):
     bank_number_regex = "\d{9}"
     batch_num_regex = "BATCH \d{4} TOTAL"
     for line in enumerate(lines):
+        # Check for a contract number and a bank number in the line
         if (re.search(contract_number_regex, line[1]) != None) & (re.search(bank_number_regex, line[1]) != None):
+            # Iterates through the columns list and adds the corresponding slot number to the dictonary for the column
+            # Here the order of the columns (keys in dictonary) matter since they need to be in the same order as 
+            # the slot numbers
             [extracted_data_dict[columns[c]].append(data_extractor(c, line[1])) for c in range(0, len(columns)-3)]
+        # This searches for a statement that looks like a batch number
+        # This sums the contracts by thier lessor code. A feature requested by cash apps
         if re.search(batch_num_regex, line[1]) != None:
+            # Batch number is always in characters 96 to 101
             batches["batch_num"].append(line[1][96:101])
+            # Payment date will be 2 lines below that between charactes 114 and 125
             batches["payment_date"].append(lines[line[0]+2][114:125])
+            # Lessor is just the first three number sof the contract number
             batches["lessor"].append(extracted_data_dict["ContractNumber"][-1][0:3])
+            # Total is a number given by the report for that batch. ',' is removed so that it can be transformed into a float
             batches["total"].append(float(line[1][107:125].strip().replace(",", "")))
             batches["count"].append(float(lines[line[0]+6][107:125].strip().replace(",", "")))
+            # Any time there's a new batch we need to add this data to the dictionary up up to the currrent place
+            # So we iterate over the number of contracts and add in the newest value for each that don't have one of these values already
             [extracted_data_dict["Batch"].append(batches["batch_num"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["Batch"])))]
             [extracted_data_dict["Lessor"].append(batches["lessor"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["Lessor"])))]
             [extracted_data_dict["PaymentDate"].append(batches["payment_date"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["PaymentDate"])))]
-
+    # Now the dictioanry lists should all be equal lengths and we can create a dataframe
     dataframe = pd.DataFrame(extracted_data_dict)
+    # We're creating two sheets: data & summary so we need to open and excel writer
+    # This also helps with a bug caused by larger dataframes
     with pd.ExcelWriter(save_name) as writer:  
         dataframe.to_excel(writer, index=False, sheet_name="data")
+        # The batches dictioanry is converted to a dataframe and added as it's own sheet
         pd.DataFrame(batches).to_excel(writer, index=False, sheet_name="Summary")
     return dataframe
 
@@ -226,6 +199,7 @@ def disposition(report: str, save_name: str):
     for line in enumerate(lines):
         if re.search(contract_number_regex, data_extractor(0,line[1])):
             [extracted_data_dict[columns[c]].append(data_extractor(c,line[1])) for c in range(0, len(columns)-1)]
+            # Customer name is on a seperate line so we need to grab that seperately
             extracted_data_dict["Customer Name"].append(lines[line[0]+1].strip())
     dataframe = pd.DataFrame(extracted_data_dict)
     dataframe.to_excel(save_name, index=False)
@@ -284,8 +258,11 @@ def gainloss(report: str, save_name: str):
     # L5: CTD OPER
     columns = list(extracted_data_dict.keys())
     # These line data are used to tell the data extrator which values to pull for each line of
-    # relevant data. It parits dictionary keys with thier corresponding data slot in the line
+    # relevant data. It pairs dictionary keys with thier corresponding data slot in the line
-    # So that they can be iterated through during data extraction
+    # so that they can be iterated through during data extraction
+    #
+    # It looks confusing but makes more sense if you look at the actual Info Lease reports
+    # This is one of the messiest reports 
     line0 = list(zip(columns[0:7],[i for i in range(1,8)]))
     line1 = list(zip(columns[7:15],[i for i in range(0,8)]))
     line2 = list(zip(columns[15:23], [i for i in range(0,8)]))
@@ -294,6 +271,7 @@ def gainloss(report: str, save_name: str):
     line5 = list(zip(columns[36:], [i for i in range(1,4)]))
     data_extractor = create_line_divider([27,43,58,74,88,105,120])
     for line in enumerate(lines):
+        # The line must contain a contract number and the first data slot should be a float
         if (re.search(contract_number_regex, data_extractor(0,line[1])) != None)&\
             (type(data_extractor(1,line[1])) == float) :
             data_section = lines[line[0]-1:line[0]+5]
@@ -345,25 +323,74 @@ def net_invest_trial_balance(report: str, save_name: str):
         'UNPAID INT' :  [],
         'NET INV' :  [],
         'UNEARNED IDC' :  [],
+        "LESSOR": []
     }
+    lessors = []
     columns = list(extracted_data_dict.keys())
     line0 = list(zip(columns[0:4], [0,3,4,5]))
     line1 = list(zip(columns[4:12], [i for i in range(0,8)]))
     line2 = list(zip(columns[12:19], [i for i in range(0,7)]))
-    line3 = list(zip(columns[19:], [i for i in range(1,6)]))
+    line3 = list(zip(columns[19:-1], [i for i in range(1,6)]))
+
+    for l in [line0,line1,line2,line3]:
+        print(f"\n{l}")
 
-    data_extractor = create_line_divider([18,35,53,67,87,106,117])
+    data_extractor = create_line_divider([18,32,50,66,84,100,117])
     for line in enumerate(lines):
         slot1 = data_extractor(0,line[1],False)
         if type(slot1) != str : continue
         if re.search(contract_number_regex, slot1) != None:
-                data_section = lines[line[0]-1:line[0]+4]
+                data_section = lines[line[0]-1:line[0]+3]
-                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[0])) for c in line0]
+                # There were issues were the IL Report would have random blank lines so that needs to be checked 
-                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[1])) for c in line1]
+                # and adjusted for
-                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[2])) for c in line2]
+                # A dead give away of an empty line in a data section is a line without a '.'
-                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[3])) for c in line3]
+                # Check the first data line
+                if data_section[0].find(".") == -1:
+                    # Move it back if empty
+                    data_section[0] = lines[line[0]-2]
+                # Now we go through each relevant data line and make sure they're not blank
+                for ds in enumerate(data_section):
+                    if ds[1].find(".") == -1:
+                        if ds[0] < len(data_section) -1:
+                            for i in range(ds[0], len(data_section)-1):
+                                # This allows us to move down all the data lines after a blank data line
+                                data_section[i] = data_section[i+1]
+                            # This handles the last data line which goes 'out-of-bounds' of the existing data selection
+                            data_section[3] = lines[line[0]+3]
+                        else:
+                            data_section[3] = lines[line[0]+3]
+                # Now that the datasection is sorted we can extract the data
+                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[0], False)) for c in line0]
+                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[1], False)) for c in line1]
+                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[2], False)) for c in line2]
+                [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[3], False)) for c in line3]
+                extracted_data_dict["LESSOR"].append(extracted_data_dict["LEASE NUMBER"][-1][0:3])
+                # We keep track of when we see new lessors for a summary tab
+                if extracted_data_dict["LESSOR"][-1] not in lessors:
+                    lessors.append(extracted_data_dict["LESSOR"][-1])      
+
     dataframe = pd.DataFrame(extracted_data_dict)
-    dataframe.to_excel(save_name, index=False)
+
+    summary_series = []
+    for lessor in lessors:
+        reduced_df = dataframe.loc[dataframe["LESSOR"] == lessor]
+        # Delete columns that are strings as we don't need to sum them
+        del reduced_df["CUSTOMER NAME"]
+        del reduced_df["LEASE NUMBER"]
+        del reduced_df["CONTRACT STAT"]
+        reduced_df = reduced_df.replace("", np.NaN)
+        # There can sometimes be REVOLVING ACCOUNT over part of the data
+        # Just get rid of it
+        reduced_df = reduced_df.replace("REVOLV", np.NaN)
+        reduced_df = reduced_df.replace("ING ACCOUNT", np.NaN)
+        summation = reduced_df.sum(skipna=True, axis=0)
+        summation["LESSOR"] = lessor
+        summation["CONTRACT COUNT"] = len(reduced_df.index)
+        summary_series.append(summation)
+    summary_df = pd.concat(summary_series, axis=1).transpose().set_index("LESSOR")
+    with pd.ExcelWriter(save_name) as writer:  
+        dataframe.to_excel(writer, index=False, sheet_name="data")
+        pd.DataFrame(summary_df).to_excel(writer, index=True, sheet_name="Summary")
     return dataframe
 
 
@@ -493,21 +520,21 @@ def renewal_net_invest_trial_balance(report: str, save_name: str):
         'CUSTOMER NAME' :  [],
         'TYPE' :  [],
         'GROSS RENEWAL' :  [],
-        'CUR RENT RCVB' :  [],
+        'REMAINING BAL' :  [],
-        'UNEARNED RIN' :  [],
+        'FINANCED RES' :  [],
         'REMAINING RES' :  [],
         'LEASE PYMTS' :  [],
         'CONTRACT NUMBER' :  [],
         'RENEWAL' :  [],
         'PAYMENTS RCVD' :  [],
-        'REM RENT RCVB' :  [],
+        'CUR RENT RCVB' :  [],
-        'UNPAID RES' :  [],
+        'UNEARNED RIN' :  [],
         'SECURITY DEP' :  [],
         'NET INVEST' :  [],
         'UNEARN INCOME' :  [],
         'TOTAL' :  [],
-        'REMAINING BAL' :  [],
+        'REM RENT RCVB' :  [],
-        'FINANCED RES' :  [],
+        'UNPAID RES' :  [],
     }
     columns = list(extracted_data_dict.keys())
     line0 = list(zip(columns[0:7], [0,1,2,3,4,5,7]))
@@ -518,7 +545,19 @@ def renewal_net_invest_trial_balance(report: str, save_name: str):
         slot1 = data_extractor(0,line[1],False)
         if type(slot1) != str : continue
         if re.search(contract_number_regex, slot1) != None:
-            data_section = lines[line[0]-1:line[0]+4]
+            data_section = lines[line[0]-1:line[0]+2]
+            # SEE net_invest_trial_balance FOR EXPLAINATION
+            if data_section[0].find(".") == -1:
+                    data_section[0] = lines[line[0]-2]
+            for ds in enumerate(data_section):
+                if ds[1].find(".") == -1:
+                    if ds[0] < len(data_section) -1:
+                        for i in range(ds[0], len(data_section)-1):
+                            data_section[i] = data_section[i+1]
+                        data_section[2] = lines[line[0]+2]
+                    else:
+                        data_section[2] = lines[line[0]+2]
+
             [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[0])) for c in line0]
             [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[1])) for c in line1]
             [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[2])) for c in line2]

RenewalTest.py

@@ -72,11 +72,16 @@ def renewal_net_invest_trial_balance(report: str, save_name: str):
         if re.search(contract_number_regex, slot1) != None:
             data_section = lines[line[0]-1:line[0]+2]
 
+            if data_section[0].find(".") == -1:
+                    data_section[0] = lines[line[0]-2]
             for ds in enumerate(data_section):
-                print(ds[1])
                 if ds[1].find(".") == -1:
-                    [print(f"\n{d[0]}: {d[1]}") for d in enumerate(data_section)]
+                    if ds[0] < len(data_section) -1:
-                    print('\n')
+                        for i in range(ds[0], len(data_section)-1):
+                            data_section[i] = data_section[i+1]
+                        data_section[2] = lines[line[0]+2]
+                    else:
+                        data_section[2] = lines[line[0]+2]
 
             [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[0])) for c in line0]
             [extracted_data_dict[c[0]].append(data_extractor(c[1], data_section[1])) for c in line1]
@@ -89,4 +94,4 @@ def renewal_net_invest_trial_balance(report: str, save_name: str):
 with open("/config/workspace/LEAF/IL Extract SRC/2022.05.20 Renewal Net Investment", errors="replace") as rep_file:
     report = rep_file.read()
 
-prt(renewal_net_invest_trial_balance(report, "rn_TESTING.xlsx"))
+prt(renewal_net_invest_trial_balance(report, "RN_TEST_0606.xlsx"))

ach_special.py

@@ -0,0 +1,87 @@
+import os
+import pandas as pd
+from datetime import datetime as dt, timedelta
+import sys, getopt
+import re
+from pathlib import Path
+import time
+from pprint import pprint as prt
+
+contract_number_regex = "\d{3}-\d{7}-\d{3}"
+
+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
+        """
+        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]
+        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 ach(report: str, save_name: str):
+
+    lines = report.splitlines()
+    extracted_data_dict = {
+    "ContractNumber" : [],
+    "CustomerName" : [],
+    "BankCode" : [],
+    "BankNumber": [],
+    "AccountNumber" : [],
+    "Payment" : [],
+    "Batch": [],
+    "Lessor": [],
+    "PaymentDate": [],
+    }
+    columns = list(extracted_data_dict.keys())
+    batches = {
+        "batch_num": [],
+        "payment_date": [],
+        "lessor": [],
+        "count": [],
+        "total": []
+    }
+
+    data_extractor = create_line_divider([19,57,67,82,104])
+    bank_number_regex = "\d{9}"
+    batch_num_regex = "BATCH \d{4} TOTAL"
+    for line in enumerate(lines):
+        if (re.search(contract_number_regex, line[1]) != None) & (re.search(bank_number_regex, line[1]) != None):
+            [extracted_data_dict[columns[c]].append(data_extractor(c, line[1])) for c in range(0, len(columns)-3)]
+        if re.search(batch_num_regex, line[1]) != None:
+            batches["batch_num"].append(line[1][96:101])
+            batches["payment_date"].append(lines[line[0]+2][114:125])
+            batches["lessor"].append(extracted_data_dict["ContractNumber"][-1][0:3])
+            batches["total"].append(float(line[1][107:125].strip().replace(",", "")))
+            batches["count"].append(float(lines[line[0]+6][107:125].strip().replace(",", "")))
+            [extracted_data_dict["Batch"].append(batches["batch_num"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["Batch"])))]
+            [extracted_data_dict["Lessor"].append(batches["lessor"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["Lessor"])))]
+            [extracted_data_dict["PaymentDate"].append(batches["payment_date"][-1]) for _ in range(0, (len(extracted_data_dict["BankCode"]) - len(extracted_data_dict["PaymentDate"])))]
+
+    dataframe = pd.DataFrame(extracted_data_dict)
+    
+    return dataframe
+
+with open("/config/workspace/LEAF/IL Extract SRC/2022.05.04_ACH_C") as rep_file:
+    report = rep_file.read()
+
+prt(ach(report, "ACH_TESTING.xlsx"))

copy.svg

@@ -0,0 +1,60 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 19.1.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 64 64" enable-background="new 0 0 64 64" xml:space="preserve">
+<g id="Text-files">
+	<path d="M53.9791489,9.1429005H50.010849c-0.0826988,0-0.1562004,0.0283995-0.2331009,0.0469999V5.0228
+		C49.7777481,2.253,47.4731483,0,44.6398468,0h-34.422596C7.3839517,0,5.0793519,2.253,5.0793519,5.0228v46.8432999
+		c0,2.7697983,2.3045998,5.0228004,5.1378999,5.0228004h6.0367002v2.2678986C16.253952,61.8274002,18.4702511,64,21.1954517,64
+		h32.783699c2.7252007,0,4.9414978-2.1725998,4.9414978-4.8432007V13.9861002
+		C58.9206467,11.3155003,56.7043495,9.1429005,53.9791489,9.1429005z M7.1110516,51.8661003V5.0228
+		c0-1.6487999,1.3938999-2.9909999,3.1062002-2.9909999h34.422596c1.7123032,0,3.1062012,1.3422,3.1062012,2.9909999v46.8432999
+		c0,1.6487999-1.393898,2.9911003-3.1062012,2.9911003h-34.422596C8.5049515,54.8572006,7.1110516,53.5149002,7.1110516,51.8661003z
+		 M56.8888474,59.1567993c0,1.550602-1.3055,2.8115005-2.9096985,2.8115005h-32.783699
+		c-1.6042004,0-2.9097996-1.2608986-2.9097996-2.8115005v-2.2678986h26.3541946
+		c2.8333015,0,5.1379013-2.2530022,5.1379013-5.0228004V11.1275997c0.0769005,0.0186005,0.1504021,0.0469999,0.2331009,0.0469999
+		h3.9682999c1.6041985,0,2.9096985,1.2609005,2.9096985,2.8115005V59.1567993z"/>
+	<path d="M38.6031494,13.2063999H16.253952c-0.5615005,0-1.0159006,0.4542999-1.0159006,1.0158005
+		c0,0.5615997,0.4544001,1.0158997,1.0159006,1.0158997h22.3491974c0.5615005,0,1.0158997-0.4542999,1.0158997-1.0158997
+		C39.6190491,13.6606998,39.16465,13.2063999,38.6031494,13.2063999z"/>
+	<path d="M38.6031494,21.3334007H16.253952c-0.5615005,0-1.0159006,0.4542999-1.0159006,1.0157986
+		c0,0.5615005,0.4544001,1.0159016,1.0159006,1.0159016h22.3491974c0.5615005,0,1.0158997-0.454401,1.0158997-1.0159016
+		C39.6190491,21.7877007,39.16465,21.3334007,38.6031494,21.3334007z"/>
+	<path d="M38.6031494,29.4603004H16.253952c-0.5615005,0-1.0159006,0.4543991-1.0159006,1.0158997
+		s0.4544001,1.0158997,1.0159006,1.0158997h22.3491974c0.5615005,0,1.0158997-0.4543991,1.0158997-1.0158997
+		S39.16465,29.4603004,38.6031494,29.4603004z"/>
+	<path d="M28.4444485,37.5872993H16.253952c-0.5615005,0-1.0159006,0.4543991-1.0159006,1.0158997
+		s0.4544001,1.0158997,1.0159006,1.0158997h12.1904964c0.5615025,0,1.0158005-0.4543991,1.0158005-1.0158997
+		S29.0059509,37.5872993,28.4444485,37.5872993z"/>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+<g>
+</g>
+</svg>

folder.svg

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" id="Outline" viewBox="0 0 24 24" width="512" height="512"><path d="M19,3H12.472a1.019,1.019,0,0,1-.447-.1L8.869,1.316A3.014,3.014,0,0,0,7.528,1H5A5.006,5.006,0,0,0,0,6V18a5.006,5.006,0,0,0,5,5H19a5.006,5.006,0,0,0,5-5V8A5.006,5.006,0,0,0,19,3ZM5,3H7.528a1.019,1.019,0,0,1,.447.1l3.156,1.579A3.014,3.014,0,0,0,12.472,5H19a3,3,0,0,1,2.779,1.882L2,6.994V6A3,3,0,0,1,5,3ZM19,21H5a3,3,0,0,1-3-3V8.994l20-.113V18A3,3,0,0,1,19,21Z"/></svg>

main.py

@@ -28,16 +28,20 @@ class MainWindow(QtWidgets.QMainWindow, Ui_MainWindow):
         inFile = QtWidgets.QFileDialog.getOpenFileName(self, 'Open file') 
         self.inputFileLE.setText(inFile[0])
         if inFile[0] == '' : return ''
-        print(f"Input File: {inFile}")
+        # Replacing errors fixes some UTF-8 character issues
         with open(inFile[0], errors="replace") as inF:
             txt = inF.read()
-            #print(txt)
             self.inputFilePreview.setText(txt)
         self.inputFile = inFile[0]
+        # This gets the actual file name
         inFileEnd = inFile[0].split('/')[-1]
+        # Takes just the root of the input file
         outputRoot = self.inputFile.removesuffix(inFileEnd)
+        # Automatically sets output to be in the same file as input, with a naming scheme
+        # The report type selected in the combo box will dictate the naming
         self.outputFile = f"{outputRoot}{self.reportTypeCB.currentText()}_{dt.now().strftime('%Y%m%d_%H%M')}.xlsx"
         self.outputFileLE.setText(self.outputFile)
+        # Check to make sure the user has selected the correct report type
         if self.reportTypeCB.currentText().split(" ")[-1].lower() not in self.inputFile.lower():
             print("Possibly wrong file type")
             warning = QtWidgets.QMessageBox()
@@ -45,9 +49,11 @@ class MainWindow(QtWidgets.QMainWindow, Ui_MainWindow):
             warning.setText(f"Selected report type is {self.reportTypeCB.currentText()} but input file did not contain '{self.reportTypeCB.currentText().split(' ')[-1].lower()}'!\n\
 Make sure you select the correct report type before processing!")
             s = warning.exec()
+        # Enables the process button
         self.check_ready_to_process()
 
     def setOutput(self):
+        # This allows the user to change the automatic naming and location
         outFile = QtWidgets.QFileDialog.getSaveFileName(self, "Output file name")
         if outFile[0] == '': return ''
         self.outputFileLE.setText(f"{outFile[0]}__{dt.now().strftime('%Y%m%d_%H_%M')}.xlsx")
@@ -56,15 +62,17 @@ Make sure you select the correct report type before processing!")
         self.check_ready_to_process()
     
     def check_ready_to_process(self):
+        # Makes sure there is an input and output selected before allowing processing
         self.rtp = True if ((self.inputFile != "") & (self.outputFile != "")) else False
         if self.rtp :
             self.processReportButton.setEnabled(True)
     
     def process_selection(self):
         self.inputFilePreview.setText("Processing file...")
-        with open(self.inputFile, errors="replace") as inF:
+        # If only this was python 3.10 and we could use switch statments
-            reportString = inF.read()
+        # but this should get the job done
         try:
+            # Here we set the extraction function that will be used on the report
             if self.reportTypeCB.currentText() == "ACH":
                 extract_function = ilx.ach
             elif self.reportTypeCB.currentText() == "Disposition":
@@ -91,18 +99,17 @@ Make sure you select the correct report type before processing!")
                 extract_function = ilx.payment_transactions
             elif self.reportTypeCB.currentText() == "Returned Check":
                 extract_function = ilx.payment_transactions
-
+            # This is where the actual processing happens
+            # We create an ILReport object and pass in the nessecary information
             dataframe = ilx.ILReport(
                 location= self.inputFile,
                 extraction_function=extract_function,
                 output_location=self.outputFile,
                 ).process()
-            
+            # The text preview box can have trouble loading the larger dataframes so
-            #dataframe.to_excel("test_name.xlsx", index=False, engine="xlsxwriter")
+            # they are trimmed to 500 so that the users can see if anything got messed up
             smallDF = dataframe.iloc[0:500,:]
             self.inputFilePreview.setText(smallDF.to_html(index=False))
-            print("Fin")          
-            self.openReportButton.setEnabled(True)
         except: 
             error = QtWidgets.QMessageBox()
             error.setWindowTitle('Error Processing File!')

mainWindow.ui

@@ -0,0 +1,268 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>MainWindow</class>
+ <widget class="QMainWindow" name="MainWindow">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>1001</width>
+    <height>664</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>MainWindow</string>
+  </property>
+  <widget class="QWidget" name="centralwidget">
+   <widget class="QTextBrowser" name="inputFilePreview">
+    <property name="geometry">
+     <rect>
+      <x>20</x>
+      <y>220</y>
+      <width>951</width>
+      <height>391</height>
+     </rect>
+    </property>
+   </widget>
+   <widget class="QPushButton" name="processReportButton">
+    <property name="enabled">
+     <bool>false</bool>
+    </property>
+    <property name="geometry">
+     <rect>
+      <x>20</x>
+      <y>180</y>
+      <width>250</width>
+      <height>36</height>
+     </rect>
+    </property>
+    <property name="text">
+     <string>&amp;Process Report</string>
+    </property>
+   </widget>
+   <widget class="QPushButton" name="openReportButton">
+    <property name="enabled">
+     <bool>false</bool>
+    </property>
+    <property name="geometry">
+     <rect>
+      <x>280</x>
+      <y>180</y>
+      <width>241</width>
+      <height>36</height>
+     </rect>
+    </property>
+    <property name="text">
+     <string>&amp;Copy to Clipboard</string>
+    </property>
+   </widget>
+   <widget class="QWidget" name="layoutWidget">
+    <property name="geometry">
+     <rect>
+      <x>21</x>
+      <y>90</y>
+      <width>951</width>
+      <height>84</height>
+     </rect>
+    </property>
+    <layout class="QVBoxLayout" name="fileSettingsBox">
+     <item>
+      <layout class="QHBoxLayout" name="inputFileBox">
+       <item>
+        <widget class="QPushButton" name="inputFileButton">
+         <property name="minimumSize">
+          <size>
+           <width>250</width>
+           <height>0</height>
+          </size>
+         </property>
+         <property name="maximumSize">
+          <size>
+           <width>250</width>
+           <height>36</height>
+          </size>
+         </property>
+         <property name="text">
+          <string>Select &amp;InfoLease Report</string>
+         </property>
+         <property name="icon">
+          <iconset>
+           <normaloff>../../.designer/backup/Pictures/svgs/folder.svg</normaloff>../../.designer/backup/Pictures/svgs/folder.svg</iconset>
+         </property>
+        </widget>
+       </item>
+       <item>
+        <widget class="QLineEdit" name="inputFileLE">
+         <property name="readOnly">
+          <bool>true</bool>
+         </property>
+         <property name="placeholderText">
+          <string>No file selected</string>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </item>
+     <item>
+      <layout class="QHBoxLayout" name="outFileLocation">
+       <item>
+        <widget class="QPushButton" name="outputFileButton">
+         <property name="minimumSize">
+          <size>
+           <width>250</width>
+           <height>0</height>
+          </size>
+         </property>
+         <property name="maximumSize">
+          <size>
+           <width>250</width>
+           <height>36</height>
+          </size>
+         </property>
+         <property name="text">
+          <string>Select &amp;Report Output Location</string>
+         </property>
+         <property name="icon">
+          <iconset>
+           <normaloff>../../.designer/backup/Pictures/svgs/folder.svg</normaloff>../../.designer/backup/Pictures/svgs/folder.svg</iconset>
+         </property>
+        </widget>
+       </item>
+       <item>
+        <widget class="QLineEdit" name="outputFileLE">
+         <property name="readOnly">
+          <bool>true</bool>
+         </property>
+         <property name="placeholderText">
+          <string>No location selected</string>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </item>
+    </layout>
+   </widget>
+   <widget class="QComboBox" name="reportTypeCB">
+    <property name="geometry">
+     <rect>
+      <x>21</x>
+      <y>51</y>
+      <width>250</width>
+      <height>37</height>
+     </rect>
+    </property>
+    <item>
+     <property name="text">
+      <string>ACH</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Disposition</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Gain Loss</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Lock Box</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Minv_C</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Net Inv. Loans</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>NI Renewal</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>NIV After</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>PBP / Epay</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Returned Check</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Unapplied</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>VMCC</string>
+     </property>
+    </item>
+    <item>
+     <property name="text">
+      <string>Wires</string>
+     </property>
+    </item>
+   </widget>
+   <widget class="QLabel" name="reportTypeL">
+    <property name="geometry">
+     <rect>
+      <x>21</x>
+      <y>21</y>
+      <width>144</width>
+      <height>24</height>
+     </rect>
+    </property>
+    <property name="font">
+     <font>
+      <pointsize>14</pointsize>
+      <weight>75</weight>
+      <bold>true</bold>
+     </font>
+    </property>
+    <property name="text">
+     <string>Infolease Report</string>
+    </property>
+    <property name="buddy">
+     <cstring>reportTypeCB</cstring>
+    </property>
+   </widget>
+  </widget>
+  <widget class="QMenuBar" name="menubar">
+   <property name="geometry">
+    <rect>
+     <x>0</x>
+     <y>0</y>
+     <width>1001</width>
+     <height>29</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QStatusBar" name="statusbar"/>
+ </widget>
+ <tabstops>
+  <tabstop>reportTypeCB</tabstop>
+  <tabstop>inputFileButton</tabstop>
+  <tabstop>outputFileButton</tabstop>
+  <tabstop>processReportButton</tabstop>
+  <tabstop>openReportButton</tabstop>
+  <tabstop>inputFileLE</tabstop>
+  <tabstop>outputFileLE</tabstop>
+  <tabstop>inputFilePreview</tabstop>
+ </tabstops>
+ <resources/>
+ <connections/>
+</ui>

process.svg

@@ -0,0 +1 @@
+<svg width="16px" height="16px" viewBox="0 0 16 16" xmlns="http://www.w3.org/2000/svg" fill="currentColor"><path fill-rule="evenodd" clip-rule="evenodd" d="M1.5 2h13l.5.5V9h-1V6H2v7h7v1H1.5l-.5-.5v-11l.5-.5zM2 5h12V3H2v2zm5 7v-1.094a1.633 1.633 0 0 1-.469-.265l-.945.539-.5-.86.937-.547a1.57 1.57 0 0 1 0-.547l-.937-.546.5-.86.945.54c.151-.12.308-.209.469-.266V7h1v1.094a1.48 1.48 0 0 1 .469.265l.945-.539.5.86-.937.547a1.57 1.57 0 0 1 0 .546l.937.547-.5.86-.945-.54a1.807 1.807 0 0 1-.469.266V12H7zm-.25-2.5c0 .208.073.385.219.531a.723.723 0 0 0 .531.219.723.723 0 0 0 .531-.219.723.723 0 0 0 .219-.531.723.723 0 0 0-.219-.531.723.723 0 0 0-.531-.219.723.723 0 0 0-.531.219.723.723 0 0 0-.219.531zm5.334 5.5v-1.094a1.634 1.634 0 0 1-.469-.265l-.945.539-.5-.86.938-.547a1.572 1.572 0 0 1 0-.547l-.938-.546.5-.86.945.54c.151-.12.308-.209.47-.266V10h1v1.094a1.486 1.486 0 0 1 .468.265l.945-.539.5.86-.937.547a1.562 1.562 0 0 1 0 .546l.937.547-.5.86-.945-.54a1.806 1.806 0 0 1-.469.266V15h-1zm-.25-2.5c0 .208.073.385.219.531a.723.723 0 0 0 .531.219.723.723 0 0 0 .531-.219.723.723 0 0 0 .22-.531.723.723 0 0 0-.22-.531.723.723 0 0 0-.53-.219.723.723 0 0 0-.532.219.723.723 0 0 0-.219.531z"/></svg>