Fixed work multi-processing & creates combined monthly

types)
Saving wach report type in a seperate excel file. Will combine later.

Still need to remove logger to enable multithreading

.gitignore

@@ -1,10 +1,14 @@
 build/
 venv/
 dist/
-inputFiles/
+InputFiles/
 __pycache__/
-2023/
 
 *.spec
 *.log
-*.xlsx
+*.xlsx
+*.txt
+*.md
+
+!todo.md
+!requirements.txt

IL Extract.spec

@@ -5,10 +5,10 @@ block_cipher = None
 
 
 a = Analysis(
-    ['main.py'],
+    ['src/il_extract.py'],
-    pathex=[],
+    pathex=['src'],
     binaries=[],
-    datas=[('assets/extract.svg', '.'), ('assets/process.svg', '.'), ('assets/folder.svg', '.'), ('assets/copy.svg', '.'), ('settings.json', '.')],
+    datas=[('src/assets/*', 'assets'), ('settings.json', '.')],
     hiddenimports=[],
     hookspath=[],
     hooksconfig={},
@@ -37,7 +37,7 @@ exe = EXE(
     target_arch=None,
     codesign_identity=None,
     entitlements_file=None,
-    icon='assets\\extract.ico',
+    icon='src/assets/extract.ico',
 )
 coll = COLLECT(
     exe,

compile_gui

@@ -1 +0,0 @@
-pyinstaller -w --add-data "assets/extract.svg;." --add-data "assets/process.svg;." --add-data "assets/folder.svg;." --add-data "assets/copy.svg;." --add-data "settings.json;." -i assets/extract.ico -n "IL Extract" main.py

ile_installer.py

@@ -1,118 +0,0 @@
-from os import system, getlogin
-import os
-from sys import exit
-from zipfile import ZipFile
-import win32com.client
-from glob import glob
-import re
-
-from itertools import cycle
-from shutil import get_terminal_size
-from threading import Thread
-from time import sleep
-
-def error_exit(exception_info: str):
-    print(exception_info)
-    input("\nPress enter/return to exit")
-    exit(1)
-
-
-class NoMatchingFile(Exception):
-    def __init__(self, search_file: str, found: list) -> None:
-        super().__init__(f"File: {search_file} was not found: {found}")
-
-
-class Loader:
-    def __init__(self, desc="Loading...", end="Done!", timeout=0.1):
-        """
-        A loader-like context manager
-
-        Args:
-            desc (str, optional): The loader's description. Defaults to "Loading...".
-            end (str, optional): Final print. Defaults to "Done!".
-            timeout (float, optional): Sleep time between prints. Defaults to 0.1.
-        """
-        self.desc = desc
-        self.end = end
-        self.timeout = timeout
-
-        self._thread = Thread(target=self._animate, daemon=True)
-        self.steps = ["|", "/", "-", "\\",]
-        self.done = False
-
-    def start(self):
-        self._thread.start()
-        return self
-
-    def _animate(self):
-        for c in cycle(self.steps):
-            if self.done:
-                break
-            print(f"\r{self.desc} {c}", flush=True, end="")
-            sleep(self.timeout)
-
-    def __enter__(self):
-        self.start()
-
-    def stop(self):
-        self.done = True
-        cols = get_terminal_size((80, 20)).columns
-        print("\r" + " " * cols, end="", flush=True)
-        print(f"\r{self.end}", flush=True)
-
-    def __exit__(self, exc_type, exc_value, tb):
-        # handle exceptions with those variables ^
-        self.stop()
-
-ZIP_LOCATION = r"\\leafnow.com\public\Accounting Shared\ILE Apps"
-APP_FOLDER = r"InfoLeaseExtract"
-
-try:
-        
-    user = getlogin()
-    install_folder = f"C:\\Users\\{user}\\AppData\\Local"
-    backup_install_folder = f"C:\\Users\\{user}\\Documents\\"
-
-    print(f"Initalizing InfoLease Extract Installer\n#######################################")
-    # Find the newest version: 
-    latest_version = glob(f"{ZIP_LOCATION}\\LATEST*")
-    if len(latest_version) == 0:
-        # Create Custom exception
-        raise NoMatchingFile(f"{ZIP_LOCATION}\\LATEST*", latest_version)
-
-    latest_version: str = latest_version[0]
-    version = re.search("\d+\.\d+", latest_version).group()
-    print(f"Installing verion {version}...")
-
-    with ZipFile(latest_version, 'r') as zipObj:
-        try:
-            with Loader("Setting up program files..."):
-                zipObj.extractall(install_folder)
-        except Exception as e:
-            error_exit(f"Failed to extract file ({latest_version}) to '{install_folder}' :\n{e}")   
-    
-    print("Creating Desktop shortcut...")
-    try:
-        desktop = f"C:\\Users\\{user}\\OneDrive - LEAF Commercial Capital\\Desktop" 
-        shell = win32com.client.Dispatch("WScript.Shell")
-        shortcut = shell.CreateShortCut(os.path.join(desktop, "IL Extract v3.10.lnk"),)
-        shortcut.Targetpath = f"{install_folder}\\IL Extract\\IL Extract.exe"
-        shortcut.IconLocation = f"{install_folder}\\IL Extract\\assets\\extract.ico"
-        shortcut.WorkingDirectory = f"{install_folder}\\IL Extract"
-        shortcut.save()
-    except:
-        try:
-            desktop = f"C:\\Users\\{user}\\Desktop" 
-            shell = win32com.client.Dispatch("WScript.Shell")
-            shortcut = shell.CreateShortCut(os.path.join(desktop, "IL Extract v3.10.lnk"),)
-            shortcut.Targetpath = f"{install_folder}\\IL Extract\\IL Extract.exe"
-            shortcut.IconLocation = f"{install_folder}\\IL Extract\\assets\\extract.ico"
-            shortcut.WorkingDirectory = f"{install_folder}\\IL Extract"
-            shortcut.save()
-        except Exception as e:
-            error_exit(f"Failed to create shortcut. The application is still installed at:\n{install_folder}\\IL Extract.\nYou can manually create a shortcut if you would like.\n{e}")
-
-    print(f"\nInstallation Completed Successfully!")
-    input("\nPress Enter/Return to exit.")
-except Exception as e:
-    error_exit(f"High level exception:\n{e}")

report_config_termplate.toml

@@ -0,0 +1 @@
+name = "Test Name"

settings.json

@@ -1 +1 @@
-{"debug": false, "consolidatedBasePath": "leafnow.com/shared/cashapps", "defaultLocations": {"ach": "", "disp": "", "gl": "", "lb": "", "minv": "", "niv": "", "ren": "", "pymt": "", "uap": "", "pastdue": ""}}
+{"debug": true, "consolidatedBasePath": ".", "defaultLocations": {"ach": "Z:/Business Solutions/Griff/Code/InfoLeaseExtract/InputFiles", "disp": "", "gl": "", "lb": "Z:/Business Solutions/Griff/Code/InfoLeaseExtract/InputFiles", "minv": "", "niv": "", "ren": "", "pymt": "Z:/Business Solutions/Griff/Code/InfoLeaseExtract/InputFiles", "uap": "", "pastdue": ""}}

src/back_reporting.py

@@ -0,0 +1,242 @@
+from pathlib import Path
+import re
+from re import Pattern
+import pandas as pd
+from pandas import DataFrame, ExcelWriter, read_excel
+from datetime import datetime as dt, timedelta
+import logging
+import il_reports as ilr
+from dataclasses import dataclass
+from typing import Callable
+from tqdm import tqdm
+from multiprocessing import Pool, cpu_count
+import os
+
+TOP_PATH: Path = Path(r"\\leafnow.com\shared\Accounting\CASH APPS\2023")
+
+class LevelFilter(object):
+    def __init__(self, level):
+        self.__level = level
+
+    def filter(self, logRecord):
+        return logRecord.levelno == self.__level
+
+def create_logger(logger_name: str = __name__, ):
+    logger = logging.getLogger(logger_name)
+
+    log_folder = Path(r"\\leafnow.com\shared\Business Solutions\Griff\Code\InfoLeaseExtract\logs")
+    fail_handler = logging.FileHandler(Path(log_folder,"Fail_br.log"), 'w')
+    fail_handler.setLevel(logging.WARNING)
+
+    info_handler = logging.FileHandler(Path(log_folder,"Info_br.log"), 'w')
+    info_handler.setLevel(logging.INFO)
+    info_handler.addFilter(LevelFilter(logging.INFO))
+
+    debug_handler = logging.FileHandler(Path(log_folder,"Debug_br.log"), 'w')
+    debug_handler.setLevel(logging.DEBUG)
+    debug_handler.addFilter(LevelFilter(logging.DEBUG))
+
+    s_handler = logging.StreamHandler()
+    s_handler.setLevel(logging.INFO)
+
+    logger.addHandler(fail_handler)
+    logger.addHandler(info_handler)
+    logger.addHandler(debug_handler)
+    logger.addHandler(s_handler)
+    
+    return logger
+   
+logger = create_logger()
+
+@dataclass
+class ExtractInstruction:
+    input_regex: Pattern
+    sheet_name: str
+    extract_method: Callable
+
+@dataclass
+class ReportFolder:
+    folder_name: Path
+    extraction_methods: list[ExtractInstruction]
+
+def extract_date_path(path: Path) -> Path:
+    date_pattern = re.compile(r'^\d{4}\.\d{2}$')
+
+    for parent in path.parents:
+        if date_pattern.match(parent.name):
+            return parent
+    return None
+
+def append_to_consolidated_report( report_path: Path, report_df: DataFrame, sheet_name: str):
+        """
+        """
+
+        report_month: Path = extract_date_path(report_path)
+        report_name: str = f"{str(report_month.name).replace('.','-')}_{sheet_name}_ConsolidatedReport.xlsx"
+
+
+        save_path = Path(r"\\leafnow.com\shared\Business Solutions\Griff\Code\InfoLeaseExtract\2023",report_name)
+        logger.debug(f"{save_path=}")
+        # Check if the current month has a consolidated report
+        
+        if not save_path.exists():
+            logger.debug(f"Consolidated Report | No monthly summary file!\n\tCreating: {save_path}")
+            # No file exists yet
+            # Create it and add the current month
+            try:
+                with pd.ExcelWriter(save_path) as writer:  
+                    logger.debug(f"Consolidated Report | {sheet_name}: Saving data as: {report_name}")
+                    report_df.to_excel(writer, index=False, sheet_name=sheet_name) 
+            except Exception as e:
+                    logger.error(f"Failed to create to consolidated report! {report_name} | {sheet_name} | {report_path} :\n{e}")
+                
+        else:
+            # We need to read the dataframe in the current monthly report
+            # Check that we are not adding matching data
+            # Save the new report
+            #FIXME: This is so hacky it's embaressing
+            try:
+                current_data_len = len(pd.read_excel(save_path,sheet_name=sheet_name))
+                with pd.ExcelWriter(save_path, engine='openpyxl', mode='a',if_sheet_exists="overlay") as writer:  
+                    logger.debug(f"Consolidated Report | {sheet_name}: Saving data as: {report_name}")
+                    report_df.to_excel(writer, index=False, sheet_name=sheet_name,startrow=current_data_len,header=False)
+            except Exception as e:
+                    logger.error(f"Failed to append to consolidated report! {report_name} | {sheet_name} | {report_path} :\n{e}")
+
+def process_report(file: Path, extract_inst: ExtractInstruction) -> bool:
+
+    try:
+        with open(str(file), errors="replace") as f:
+            report_str: str = f.read()
+            #logger.debug(f"{report_str}")
+            try:
+                df: DataFrame = extract_inst.extract_method(report_str, None)
+                if df.empty:
+                    raise ValueError("Dataframe is empty!")
+            except Exception as e:
+                logger.warning(f"Failed to create report df: {extract_inst.sheet_name}:\n{e}")
+                return False
+            append_to_consolidated_report(file, df, extract_inst.sheet_name)
+            return True
+    except Exception as e:
+        logger.exception(f"could not process {file}:\n{e}")
+        return False
+
+def process_folder(folder: ReportFolder):
+                
+        # Search recurively through date directories
+        report_date: dt = dt(2023, 5, 1)
+        while report_date.date() < dt.now().date():
+            logger.info(f"{folder.folder_name} | Processing date: {report_date}")
+            report_folder: Path = Path(TOP_PATH, 
+                report_date.strftime("%Y.%m"),
+                report_date.strftime("%Y.%m.%d"),
+                folder.folder_name
+            )
+            logger.debug(f"report_folder: {report_folder}")
+            if report_folder.exists():
+                for xi in folder.extraction_methods:
+                    try:
+                        files = report_folder.glob(f"*{xi.input_regex}*")
+                        report_file: Path = next(files)
+                        logger.debug(f"Report file: {report_file}")
+                    except IndexError as ie:
+                        logger.warning(f"No matching reports!: {ie}")
+                    except Exception as e:
+                        logger.debug(f"Could not get report_file: {report_folder.glob(f'*{xi.input_regex}*')} \n{e}")
+                        continue
+                    try:
+                        success = process_report(report_file, xi)
+                        if success:
+                            logger.info(f"Report Processed: {report_file} | {xi.sheet_name}")
+                        else:
+                            logger.warning(f"Failed to process report: {report_file} | {xi.sheet_name}")
+
+                    except Exception as e:
+                        logger.exception(f"Could not process report ({report_file}) :\n{e}")
+                        continue
+            else:
+                logger.debug(f"Folder '{report_folder}' does not exist!")
+            report_date = report_date + timedelta(days=1)
+        logger.debug(f"Finished scanning {folder.folder_name}!")
+
+
+def combine():
+    
+    WORK_DIR = Path(r"\\leafnow.com\shared\Business Solutions\Griff\Code\InfoLeaseExtract\2023")
+
+    REPORTS = [
+        "ACH",
+        "CHECKS LIVE",
+        "CREDIT CARDS",
+        "PAY BY PHONE",
+        "WIRE",
+        "RETURNS ACH",
+        "RETURNS PORTAL"
+    ] 
+    
+    for i in range(1,6):
+        
+        month = f"2023-0{i}"
+        mcr: Path = Path(f"{month} Consolidated Report.xlsx")
+        print(f"Creating monthly consolidated report: {mcr}")
+        with ExcelWriter(Path(WORK_DIR, "Monthly", mcr), engine="xlsxwriter") as wrtr:
+            for r in REPORTS:
+                report_path: Path = Path(WORK_DIR, f"{month}_{r}_ConsolidatedReport.xlsx")
+                print(f"Report Path ({r}): {report_path}")
+
+                rdf: DataFrame = read_excel(report_path, sheet_name=r)
+
+                rdf.to_excel(wrtr, sheet_name=r, freeze_panes=(1,0), index=False)
+
+if __name__ == "__main__":
+
+    
+    
+
+    FOLDERS = [
+        ReportFolder("ACH", [
+            ExtractInstruction("_ACH_", "ACH", ilr.ach),
+        ]),
+        ReportFolder("CHECKS LIVE", [
+            ExtractInstruction("_PROGPAY_BER", "CHECKS LIVE", ilr.payment_transactions)
+        ]),
+        ReportFolder("CREDIT CARDS", [
+            ExtractInstruction("_VMCC_BER", "CREDIT CARDS", ilr.payment_transactions)
+        ]),
+        ReportFolder("LOCKBOX", [
+            ExtractInstruction("_LOCKBOX_\d+_", "LOCKBOX", ilr.lockbox)
+        ]),
+        ReportFolder("PAY BY PHONE", [
+            ExtractInstruction("_PBP_EPAY_DPS_BER", "PAY BY PHONE", ilr.payment_transactions)
+        ]),
+        ReportFolder("RETURN REPORTING", [
+            ExtractInstruction("_PBP_EPAY_RETURNS_BER", "RETURNS ACH", ilr.payment_transactions),
+            ExtractInstruction("_RETURNS_BER", "RETURNS PORTAL", ilr.payment_transactions)]
+        ),
+        ReportFolder("WIRES", [
+            ExtractInstruction("MTBWIRE_BER", "WIRE", ilr.payment_transactions)
+        ]),
+    ]
+    
+    process_folder(FOLDERS[0])
+    # with Pool(cpu_count()) as pool:
+    #     for folder in tqdm(pool.imap_unordered(process_folder,FOLDERS)):
+    #         try:
+    #             print(f"Completed!")
+    #         except Exception as e:
+    #             print(f"Failed to process\n {e}")
+    #             continue
+    # for folder in tqdm(FOLDERS):
+    #     try:
+    #         process_folder(folder)
+    #         print(f"Completed: {folder.folder_name}")
+    #     except Exception as e:
+    #         print(f"Failed to process {folder.folder_name} \n {e}")
+    #         continue
+    # input("Complete!")
+
+
+
+    combine()
+

src/datasets/dataset_template.json

@@ -0,0 +1,12 @@
+{
+    "name": {
+        "report": "",
+        "excel": ""
+    },
+    "relative_position": {
+        "rows": 0,
+        "col": 0
+    },
+    "length": 0,
+    "data_type": "int"
+}

src/extractors.py

@@ -0,0 +1,184 @@
+from typing import TypeAlias, TypeVar
+from dataclasses import dataclass
+from pathlib import Path
+import pathlib as pl
+from abc import ABC, abstractmethod, abstractproperty
+from re import search, match, compile, Match, Pattern
+from enum import Enum
+
+ColumnIndex: TypeAlias = int
+Money: TypeAlias = float
+
+Numeric = TypeVar("Numeric", float, int)
+
+class Line(Enum):
+    Header: str
+    Data: str
+    Erroneous: str
+    Top: str
+    Bottom: str
+
+
+
+@dataclass
+class RelativePosition:
+    """
+    Coordinates for navigating from one point in a row to another
+    """
+    rows: int
+    col: ColumnIndex
+
+@dataclass
+class DataValue:
+ 
+    position: RelativePosition
+    length : int
+    regex: Pattern
+    dtype: type
+
+    def correct_line(self, adj_lines_since_header: int) -> bool:
+        """
+        """
+        return adj_lines_since_header % self.position.rows == 0
+    
+    def _line_slice(self, line: Line.Data) -> str|None:
+        """
+        Attempts to get the data from the line.
+        Returns string in correct postion or None if out of range.
+        """
+        try:
+            start: int = self.position.col
+            end: int = start + self.length
+            line_slice: str = line[start:end]
+        except IndexError:
+            #TODO: Add logging
+            line_slice = None
+        finally:
+            return line_slice
+    
+    @staticmethod
+    def _to_float(number_str: str) -> float|None:
+        try:
+            f_value:float = float(number_str.replace(',',''))
+            return f_value
+        except:
+            return None
+
+    def extract(self, line: Line.Data) -> type|None:
+        """
+        """
+        line_slice: str|None = self._line_slice(line)
+        if isinstance(line_slice, None): 
+            return None
+        
+        value_match: Match|None = search(self.regex, line_slice)
+        if isinstance(value_match, None): 
+            return None
+        
+        value_str: str = value_match.group()
+        
+        value_str.strip()
+        if self.dtype == int or self.dtype == float:
+            return self._to_float(value_str)
+        #TODO datetime
+        return value_str
+
+class DataSet:
+
+    def __init__(self, config: dict) -> None:
+        self.r_name = config["naming"]["report"]
+        try:
+            self.e_name = config["naming"]["excel"]
+        except KeyError:
+            self.e_name = self.r_name
+
+        self.data_value: DataValue = DataValue(
+            position = RelativePosition(
+               rows= config["relative_position"]["rows"],
+               col= config["relative_position"]["col"]
+            ),
+            length = config["length"],
+            dtype = config["data_type"],
+        )
+
+    def line_position(self, line: str) -> ColumnIndex|None:
+        """
+        Searches a line for the report header for this dataset.
+
+        Returns:
+            - ColumnIndex(int) | None: The column index of the matches end position
+            or None if no match was found
+        """
+        header_match: Match|None = search(self.r_name, line)
+        return header_match.end() if isinstance(header_match, Match) else None
+
+@dataclass
+class ReportConfig:
+
+    file_extension: str
+    name: str
+    datasets: list[DataSet]
+    data_line_regexes: list[Pattern]
+
+
+class ILReport(ABC):
+
+    def __init__(self, file_path: Path, report_config: ReportConfig) -> None:
+        self.in_file_path: Path = file_path
+        self.line_gen = self._line_generator(file_path)
+        
+        self.config: ReportConfig = report_config
+        self.name = report_config.name
+
+        self.line_type_history: list[Line] = []
+        self.last_header_line: int|None = None
+
+        self.data_dict: dict = {
+            header.e_name: [] 
+            for header in self.config.datasets 
+        }
+        
+    @staticmethod
+    def _line_generator(file_path: Path):
+        with open(file_path, 'r') as in_file:
+            line: str
+            for line in in_file.readlines():
+                yield line
+
+    def _add_line_history(self, line: Line, max_history: int = 10):
+        self.line_type_history.append(line)
+        while len(self.line_type_history) > max_history:
+            self.line_type_history.pop(0)
+
+    def _is_header_line(self, line: str) -> bool:
+        """
+        Checks whether a report line has data headers.
+        """
+        regex: Pattern
+        for regex in self.config.data_line_regexes:
+            if isinstance(search(regex,line), Match):
+                return True
+        return False
+    
+    @abstractmethod
+    def _skip_line(self, line) -> bool:
+        """
+        Tells whether we should skip this line
+        """
+
+    @abstractmethod
+    def _process_line(self):
+        """
+        
+        """
+    
+    @abstractmethod
+    def _process_dataline(self, dataline: Line.Data):
+        """
+        """
+        
+# Search the row for a data set name, or list of data set names
+# extract all the data until the next row
+
+if __name__ == "__main__":
+    datasets = []

src/il_extract.py

@@ -1,20 +1,20 @@
-from ILE_MainWindow import Ui_MainWindow
+from ui_ile_main_window import Ui_MainWindow
 import sys
 import os 
 import pandas as pd 
 import json
 from PyQt5 import QtWidgets
 from datetime import datetime as dt
-import ILExtract as ilx
+import il_reports as ilx #TODO redo aliasing
 from logging import debug, DEBUG, basicConfig
 
 
 with open("settings.json") as s:
     settings = json.loads(s.read())
-    if settings["debug"]:
+    #if settings["debug"]:
-        basicConfig(filename='debug.log', encoding='utf-8', level=DEBUG)
+    basicConfig(filename='debug.log', mode='w', encoding='utf-8', level=DEBUG)
 
-debug("\n\n\n########################### VERSION = 3.10 ###########################\n\n\n")
+debug("\n\n\n########################### VERSION = 3.2 ###########################\n\n\n")
 debug("Running main.py...")
 class MainWindow(QtWidgets.QMainWindow, Ui_MainWindow):
     """
@@ -290,14 +290,16 @@ class MainWindow(QtWidgets.QMainWindow, Ui_MainWindow):
         debug(f"report_type_change | inputFile: {self.inputFile}")
         debug(f"report_type_change | outputFile: {self.outputFile}")
         self.check_ready_to_process()  
-    
+
-# Defines the app
+
-app = QtWidgets.QApplication(sys.argv)
+if __name__ == "__main__":
-# Sets the style
+    # Defines the app
-app.setStyle("Fusion")
+    app = QtWidgets.QApplication(sys.argv)
-# Builds the main window
+    # Sets the style
-window = MainWindow()
+    app.setStyle("Fusion")
-window.setWindowTitle("IL Extract")
+    # Builds the main window
-window.show()
+    window = MainWindow()
-# Starts the app
+    window.setWindowTitle("IL Extract")
-app.exec()
+    window.show()
+    # Starts the app
+    app.exec()

src/il_reports.py

@@ -8,7 +8,7 @@ import numpy as np
 from glob import glob
 from logging import debug, DEBUG, basicConfig, warn, error
 
-# V3.1 | 01/19/23
+# V3.2 | 04/21/23
 
 with open("settings.json") as s:
     settings = json.loads(s.read())
@@ -70,10 +70,14 @@ class ILReport:
             sheet_name = "CREDIT CARDS"
         elif re.search("(?i)lockbox", self.location) != None:
             sheet_name = "LOCKBOX"
+        elif re.search("(?i)PBP_EPAY_RETURNS_BER", self.location) != None:
+            sheet_name = "RETURNS ACH"
         elif re.search("(?i)epay", self.location) != None:
             sheet_name = "PAY BY PHONE"
         elif re.search("(?i)wires", self.location) != None:
             sheet_name = "WIRES"
+        elif re.search("(?i)RETURNS_BER", self.location) != None:
+            sheet_name = "RETURNS Portal"
         else:
             return None
 
@@ -102,18 +106,25 @@ class ILReport:
             # We need to read the dataframe in the current monthly report
             # Check that we are not adding matching data
             # Save the new report
-            current_data: DataFrame = pd.read_excel(month_summary_file[0], sheet_name=sheet_name)
+            #FIXME: This is so hacky it's embaressing
-            new_data_len = len(dataframe_to_append)
+            add_headers = False
-            cur_first_col = current_data.iloc[len(current_data)-new_data_len:,0].to_list()
+            try:
-            new_first_col = dataframe_to_append.iloc[:,0].to_list()
+                current_data: DataFrame = pd.read_excel(month_summary_file[0], sheet_name=sheet_name)
-            if cur_first_col == new_first_col:
+                new_data_len = len(dataframe_to_append)
-                debug(f"Consolidated Report | Data is same as previous! Skipping!")
+                cur_first_col = current_data.iloc[len(current_data)-new_data_len:,0].to_list()
-                return None
+                new_first_col = dataframe_to_append.iloc[:,0].to_list()
+                if cur_first_col == new_first_col:
+                    debug(f"Consolidated Report | Data is same as previous! Skipping!")
+                    return None
+            except ValueError as ve:
+                ve == ValueError(f"Worksheet named '{sheet_name} not found")
+                current_data = []
+                add_headers = True
             # We need to find the start cols (where the new data should go)
             try:
                 with pd.ExcelWriter(save_path, engine='openpyxl', mode='a',if_sheet_exists="overlay") as writer:  
                     debug(f"Consolidated Report | {sheet_name}: Saving data as: {report_name}")
-                    dataframe_to_append.to_excel(writer, index=False, sheet_name=sheet_name,startrow=len(current_data),header=False)
+                    dataframe_to_append.to_excel(writer, index=False, sheet_name=sheet_name,startrow=len(current_data),header=add_headers)
             except Exception as e:
                 error(f"[E] Failed to append to consolidated report! {sheet_name}:\n{e}")
    
@@ -181,7 +192,7 @@ COMMON REGEX COMPONENTS
 """
 
 
-def ach(report: str, save_name: str):
+def ach(report: str, save_name: str|None):
     debug(f"ACH Report {save_name} :\n{report}")
     lines = report.splitlines()
     extracted_data_dict = {
@@ -235,11 +246,12 @@ def ach(report: str, save_name: str):
     dataframe: DataFrame = 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:  
+    if save_name is not None:
-        debug(f"ACH: Saving data as: {save_name}")
+        with pd.ExcelWriter(save_name) as writer:  
-        dataframe.to_excel(writer, index=False, sheet_name="data")
+            debug(f"ACH: Saving data as: {save_name}")
-        # The batches dictioanry is converted to a dataframe and added as it's own sheet
+            dataframe.to_excel(writer, index=False, sheet_name="data")
-        DataFrame(batches).to_excel(writer, index=False, sheet_name="Summary")
+            # The batches dictioanry is converted to a dataframe and added as it's own sheet
+            DataFrame(batches).to_excel(writer, index=False, sheet_name="Summary")
     return dataframe
 
 def disposition(report: str, save_name: str):
@@ -614,7 +626,7 @@ def net_invest_trial_balance(report: str, save_name: str):
             writer, index=True, sheet_name="Summary")
     return dataframe
 
-def lockbox(report: str, save_name: str):
+def lockbox(report: str, save_name: str|None):
     debug(f"LockBox Report {save_name}:\n{report}")
     lines = report.splitlines()
     extracted_data_dict = {
@@ -667,7 +679,8 @@ def lockbox(report: str, save_name: str):
                 extracted_data_dict["CUST NAME"].append(lines[index+1].strip())
     dataframe = DataFrame(extracted_data_dict)
     debug(f"LockBox | Saving dataframe: {save_name}")
-    dataframe.to_excel(save_name, index=False)
+    if save_name is not None:
+        dataframe.to_excel(save_name, index=False)
     return dataframe
 
 
@@ -706,7 +719,7 @@ def minv(report: str, save_name: str):
 
 
 # Good for PUB_WIRES, VMCC, PBP_EPAY, returned check
-def payment_transactions(report: str, save_name: str):
+def payment_transactions(report: str, save_name: str|None):
     debug(f"PayTrans | {save_name}:\n{report}")
     lines = report.splitlines()
     data_extractor = create_line_divider([6,33,52,62,80,89,110,121])
@@ -743,8 +756,9 @@ def payment_transactions(report: str, save_name: str):
             extracted_data_dict['INV NO'].append(inv_no)
     dataframe = DataFrame(extracted_data_dict)
     debug(f"PayTrans | Complted Dataframe:\n{dataframe}")
-    dataframe.to_excel(save_name, index=False)
+    if save_name is not None:
-    debug(f"PayTrans | Saved to {save_name}")
+        dataframe.to_excel(save_name, index=False)
+        debug(f"PayTrans | Saved to {save_name}")
     return dataframe
 
 

src/ui_ile_main_window.py

@@ -1,3 +1,6 @@
+"""
+The user interface set up for the main window of the application
+"""
 # -*- coding: utf-8 -*-
 
 # Form implementation generated from reading ui file 'ILE_MainWindow.ui'

todo.md

@@ -0,0 +1,39 @@
+# Work List
+
+## Priority
+- [ ] Bring back in consolidated reports
+   - [X] ACH
+   - [X] CHECKS_LIVE
+   - [X] CREDIT
+   - [X] LOCKBOX
+   - [X] PAY BY PHONE
+   - [X] WIRES
+   - [ ] RETURNS ACH
+   - [ ] RETURNS Portal *(new addition)*
+
+- [ ] Adjust pyinstaller spec for new file structure
+
+- [ ] Function to recap year
+- [ ] Fix Logging
+
+## Feature Goals
+- [ ] Year Walkthrough report
+- [ ] 'In Progress' notification/spinner
+- Speed up ACH/All
+
+Generate monthly consolidated reports for each month in a year
+   - Must generate IL Extract report where nesseary
+
+- [ ] Users can add/create new reports
+   - This would be very complicated
+
+## Code Improvement
+- [ ] Rework IL Report as an ABC and report types as sub-classes
+- [ ] Rework config set up
+- [ ] Simpify & standardize row/data parsing
+
+
+## Completed last commit
+
+
+---