Notes

import tkinter as tk
from tkinter import filedialog as fd
from tkinter import messagebox
import pandas as pd
import PyPDF2
import re


class Document:
skusWithQuantities = []
skus = []
extension = ""
filetype = ''
partNumber = ""

def __init__(self,ext,ftype):
self.extension = ext
self.filetype = ftype
self.skusWithQuantities = []
self.skus = []
self.generateFromFile()

def generateFromFile(self): # gets the skus for a quote
currentQuote = open(self.extension,'rb') #open pdf document

pdfReader = PyPDF2.PdfReader(currentQuote) #establish reading connection
self.partNumber = ''
for i in pdfReader.pages: # for each page
pageNotes = str(i.extract_text()) #get all the text
self.skusWithQuantities += re.findall(stringDict[self.filetype],pageNotes) #add all matching SKUs(and quantities)

self.skus = [i[0] for i in self.skusWithQuantities] # find just the SKUs
currentQuote.close() #close pdf document

def readPages(self): #displays what the app can see
currentQuote = open(self.extension,'rb') #open pdf document
pdfReader = PyPDF2.PdfReader(currentQuote) #establish reading connection
for i in pdfReader.pages: # for each page
pageNotes = str(i.extract_text()) #get all the text
print(pageNotes)
currentQuote.close() #close pdf document




class Document:
skusWithQuantities = []
skus = []
extension = ""
filetype = ''
partNumber = ""

def __init__(self,ext,ftype):
self.extension = ext
self.filetype = ftype
self.skusWithQuantities = []
self.skus = []
self.generateFromFile()

def generateFromFile(self): # gets the skus for a quote
currentQuote = open(self.extension,'rb') #open pdf document

pdfReader = PyPDF2.PdfReader(currentQuote) #establish reading connection
self.partNumber = ''
for i in pdfReader.pages: # for each page
pageNotes = str(i.extract_text()) #get all the text
self.skusWithQuantities += re.findall(stringDict[self.filetype],pageNotes) #add all matching SKUs(and quantities)

self.skus = [i[0] for i in self.skusWithQuantities] # find just the SKUs
currentQuote.close() #close pdf document

def readPages(self): #displays what the app can see
currentQuote = open(self.extension,'rb') #open pdf document
pdfReader = PyPDF2.PdfReader(currentQuote) #establish reading connection
for i in pdfReader.pages: # for each page
pageNotes = str(i.extract_text()) #get all the text
print(pageNotes)
currentQuote.close() #close pdf document

class Quote(Document):
total = ""
quoteDate = ""
quoteNumber = ""

def __init__(self,ext,ftype):
Document.__init__(self,ext,ftype)


class EMEAQuote(Quote):
def __init__(self,ext):
Quote.__init__(self,ext,'EMEA')
baseMult = 1
newSkuWQuantity =[]
for sku,mult,count in self.skusWithQuantities:
if count == '':
baseMult = int(mult)
newSkuWQuantity.append((sku,mult))
else:
newSkuWQuantity.append((sku,str(int(count)*baseMult)))#for sku in self.skusWithQuantities
#***********add logic for combining quantities
self.skusWithQuantities = newSkuWQuantity

def getData(self):
currentQuote = open(self.extension,'rb') #open pdf document
pdfReader = PyPDF2.PdfReader(currentQuote) #establish reading connection
pageNotes = str(pdfReader.pages[0].extract_text()) #get all the text
pageTwo = str(pdfReader.pages[1].extract_text())
data1 = re.findall(EMEAQuoteData,pageNotes) #add all matching SKUs(and quantities)
data2 = re.findall(EMEAQuoteData2,pageTwo)
data3 = re.findall(EMEAQuoteData3,pageNotes)
self.quoteDate = data1[0][0]
self.quoteNumber = data1[0][1]
#print(data2)
self.total = data2[0]
self.partNumber = data3[0]
currentQuote.close() #close pdf document


def __str__(self):
self.getData()
retString = 'Emea Quote: ' + self.quoteNumber + 'n'
retString += 'Total: ' + self.total + 'n'
retString += 'Date: ' + self.quoteDate + 'n'
retString += 'Part Number: ' + self.partNumber + 'n'
return retString




class EMEAGIIvsDSAApp:
def __init__(self, master):
self.master = master
master.title("EMEA Gii vs. EMEA Dsa Quote Review")
master.geometry("400x200")

self.label = tk.Label(master, text="Compare EMEA Gii (PDF) and EMEA Dsa (Excel) Quotes")
self.label.pack(pady=10)

self.compare_button = tk.Button(master, text="Select and Compare Quotes", command=self.compare_quotes)
self.compare_button.pack(pady=20)

def compare_quotes(self):
gii_pdf_path = fd.askopenfilename(title='Select EMEA GII Quote (PDF)', filetypes=[("PDF Files", "*.pdf")])
dsa_excel_path = fd.askopenfilename(title='Select EMEA DSA Quote (Excel)', filetypes=[("Excel Files", "*.xlsx", "*.xls")])

if not gii_pdf_path or not dsa_excel_path:
messagebox.showerror("Error", "Both a PDF and an Excel file must be selected")
return

# Extract SKU data from both documents
gii_skus = self.extract_pdf_skus(gii_pdf_path)
dsa_skus, dsa_details = self.read_excel_data(dsa_excel_path)

# Compare SKUs
gii_not_in_dsa, dsa_not_in_gii = self.compare_skus(gii_skus, dsa_skus)

# Display comparison results
self.display_results(dsa_details, gii_not_in_dsa, dsa_not_in_gii)

def extract_pdf_skus(self, filepath): #gets the skus for a quote
gii_pdf_path = open(self.extension,'rb') #open pdf document

pdfReader = PyPDF2.PdfReader(gii_pdf_path) #establish reading connection
self.partNumber = ''
for i in pdfReader.pages: # for each page
pageNotes = str(i.extract_text()) #get all the text
self.skusWithQuantities += re.findall(stringDict[self.filetype],pageNotes) #add all matching SKUs(and quantities)

self.skus = [i[0] for i in self.skusWithQuantities] # find just the SKUs
currentQuote.close() #close pdf document



def read_excel_data(filepath):
"""Reads data from an Excel file, focusing on SKU and quantity extraction."""
df = pd.read_excel(filepath, usecols=["K", "N"]) # Adjust column letters as necessary
skus_with_quantities = df.groupby('K')['N'].sum().to_dict() # Sum quantities for each SKU
return skus_with_quantities



def compare_skus(pdf_skus, excel_skus):
"""Compares SKUs and quantities between PDF and Excel data."""
mismatches = []
for sku, qty in pdf_skus.items():
if sku not in excel_skus:
mismatches.append(f"SKU {sku} present in PDF not in Excel")
elif qty != excel_skus[sku]:
mismatches.append(f"Quantity mismatch for SKU {sku}: PDF has {qty}, Excel has {excel_skus[sku]}")
for sku, qty in excel_skus.items():
if sku not in pdf_skus:
mismatches.append(f"SKU {sku} present in Excel not in PDF")
return mismatches


def display_results(self, dsa_details, gii_not_in_dsa, dsa_not_in_gii):
results_window = tk.Toplevel(self.master)
results_window.title("Comparison Results")
tk.Label(results_window, text=f"EMEA Dsa Quote Details:n{dsa_details}").pack()
tk.Label(results_window, text=f"SKU present in Gii not in Dsa:n{gii_not_in_dsa}").pack()
tk.Label(results_window, text=f"SKU present in Dsa not in Gii:n{dsa_not_in_gii}").pack()

if __name__ == "__main__":
root = tk.Tk()
app = EMEAGIIvsDSAApp(root)
root.mainloop()