Update app.py

app.py

@@ -4,6 +4,24 @@ import os
 import ast
 import streamlit as st
 import pandas as pd
+import os
+from google.oauth2.credentials import Credentials
+from google.auth.transport.requests import Request
+from google_auth_oauthlib.flow import InstalledAppFlow
+from googleapiclient.discovery import build
+from googleapiclient.http import MediaIoBaseDownload,MediaFileUpload
+
+# Load credentials from environment variables
+credentials_dict = {
+    "token": os.environ.get("token"),
+    "refresh_token": os.environ.get("refresh_token"),
+    "token_uri": os.environ.get("token_uri"),
+    "client_id": os.environ.get("client_id"),
+    "client_secret": os.environ.get("client_secret"),
+    "scopes": os.environ.get("scopes")
+}
+
+MAPPING_FILENAME = "Data Mapping with ItemCode.xlsx"
 
 def convert_pdf_to_excel(pdf_file):
     inputpdf = PyPDF2.PdfReader(pdf_file)
@@ -21,6 +39,7 @@ def convert_pdf_to_excel(pdf_file):
             date_qty = []
             row_start_index = 0
             row_stop_index = 0
+            year = ""
             for index in range(len(data)):
                 if data[index].strip() == 'Part No.':
                     each_table_data.append(data[index+1].replace('Part Color Code',""))
@@ -28,6 +47,13 @@ def convert_pdf_to_excel(pdf_file):
                         each_table_data.append(data[index+2].replace('Part Color Code',""))
                     else:
                         each_table_data.append("")
+                
+                if data[index].strip()=='MORIROKU TECHNOLOGY':
+                    try:
+                        year = data[index+1].split(' ')[0].split('/')[1]
+                    except Exception as e:
+                        print(e)
+                        year = ""
 
                 if 'Part Name' in data[index].strip():
                     each_table_data.append(data[index+1])
@@ -41,7 +67,7 @@ def convert_pdf_to_excel(pdf_file):
             if row_start_index>0 and row_stop_index>0:
                 for index in range(row_start_index,row_stop_index):
                     if '/' in data[index].strip():
-                        date_qty.append([data[index].strip()[-5:].strip(),data[index+1].strip()])
+                        date_qty.append([data[index].strip()[-5:].strip() + "/"+year,data[index+1].strip()])
             if not date_qty:
                 date_qty = [["",""]]
             each_table_data.append(date_qty)
@@ -61,6 +87,8 @@ def map_data_to_template(excel_file, mapping_file):
     # Load Excel file and mapping file
     extracted_data = pd.read_excel(excel_file)
     mapping_data = pd.read_excel(mapping_file)
+    mapping_data.to_excel(MAPPING_FILENAME)
+    save_mapping_file_to_drive()
     mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
 
     # Perform mapping
@@ -68,10 +96,68 @@ def map_data_to_template(excel_file, mapping_file):
     extracted_data = extracted_data.explode('Date Qty')
     extracted_data[['SchDate','Qty']]= pd.DataFrame(extracted_data['Date Qty'].to_list(), index= extracted_data.index)
     extracted_data = extracted_data.drop('Date Qty',axis=1)
-    mapped_data = extracted_data.merge(mapping_data, on =['Part No.'])[['Item Code','SchDate','Qty']]
+    extracted_data = extracted_data[~extracted_data['SchDate'].isna()]
+    mapped_data = extracted_data.merge(mapping_data, on =['Part No.'],how='outer')#[['Item Code','SchDate','Qty']]
+    mapped_data['SOType'] = "R"
+    mapped_data = mapped_data[~mapped_data["SchDate"].isna()]
 
     return mapped_data
 
+def save_mapping_file_to_drive():
+    creds = Credentials.from_authorized_user_info(credentials_dict)
+    # Authenticate with Google Drive API
+    service = build('drive', 'v3', credentials=creds)
+    folder_id = "1HBRUZePST0D0buyU9MxeYg2vQyEL4wLF"
+
+    # List all files in the folder
+    results = service.files().list(
+        q=f"'{folder_id}' in parents and mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
+        fields="files(id, name)").execute()
+    files = results.get('files', [])
+    files = [i for i in files if i.get('name')=='Data Mapping with ItemCode.xlsx']
+
+    if not files:
+        print('No Excel Mapping files found in the folder.')
+    else:
+        for file in files:
+            # Get the ID and name of the first Excel file found in the folder
+            existing_file_id = file['id']
+            existing_file_name = file['name']
+
+            # Delete the existing file
+            service.files().delete(fileId=existing_file_id).execute()
+
+    file_metadata = {'name': MAPPING_FILENAME, 'parents': [folder_id]}
+    media = MediaFileUpload(MAPPING_FILENAME, mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet')
+    service.files().create(body=file_metadata, media_body=media, fields='id').execute()
+
+def pull_mapping_file_from_drive():
+    creds = Credentials.from_authorized_user_info(credentials_dict)
+    # Authenticate with Google Drive API
+    service = build('drive', 'v3', credentials=creds)
+
+    results = service.files().list(
+        q="mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
+        fields="files(id, name)").execute()
+    files = results.get('files', [])
+    files = [i for i in files if i.get('name')=='Data Mapping with ItemCode.xlsx']
+    if files:
+        file_id = files[0]['id']
+        file_name = files[0]['name']
+        request = service.files().get_media(fileId=file_id)
+        fh = open(file_name, 'wb')
+        downloader = MediaIoBaseDownload(fh, request)
+
+        # Execute the download
+        done = False
+        while not done:
+            status, done = downloader.next_chunk()
+
+        fh.close()
+        return 1
+    return 0
+    
+
 def main():
     st.title("PDF to Excel Converter")
     
@@ -99,12 +185,26 @@ def main():
         else:
             st.error("Error: Converted Excel file not found")
 
-        
-        st.markdown("## Upload the Data Master file with Item Code mapping")
-        mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
+        file_present = pull_mapping_file_from_drive()
+        if not os.path.exists("Data Mapping with ItemCode.xlsx"):
+            st.markdown("## Upload the Data Master file with Item Code mapping")
+            mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
+        else:
+            mapping_data = pd.read_excel("Data Mapping with ItemCode.xlsx")
+            mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
+            data_for_mapping = "Data Mapping.xlsx"
+            extracted_data_for_mapping = pd.read_excel(data_for_mapping)
+            extracted_data_for_mapping = extracted_data_for_mapping[~extracted_data_for_mapping['Part No.'].isin(mapping_data['Part No.'])]
+            unmapped_part_no = extracted_data_for_mapping['Part No.'].nunique()
+            if unmapped_part_no>0:
+                st.markdown("#### There are {} Part No. with No ItemCode present. Upload a new file after mapping them".format(unmapped_part_no))
+                mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
+            else:
+                st.markdown("#### Using the Mapping file available in Google Drive")
+                mapping_uploaded_file =  "Data Mapping with ItemCode.xlsx"
 
         if mapping_uploaded_file is not None:
-            st.write("Uploaded Mapping Excel file:", mapping_uploaded_file.name)
+            # st.write("Uploaded Mapping Excel file:", mapping_uploaded_file.name)
 
             # Perform data mapping
             mapped_data = map_data_to_template(extracted_file, mapping_uploaded_file)
@@ -126,10 +226,6 @@ def main():
                 )
             else:
                 st.error("Error: Converted Excel file not found")
-
-            
-            
-            
-        
+ 
 if __name__ == "__main__":
     main()