Update tsadropboxretrieval.py

tsadropboxretrieval.py

@@ -94,7 +94,8 @@ def dropbox_upload_file(df, flag=0):
         dbxTeam= ADR_Access_DropboxTeam('admin')
         path='/TSA JOBS/ADR Test/DropboxDirectory/df.parquet.gzip'
         doc=df.to_parquet()
-        meta=dbxTeam.files_upload(doc,path,mode=dropbox.files.WriteMode("overwrite"))
+        dbxTeam.files_delete(path)
+        meta=dbxTeam.files_upload(doc,path)
 
     except Exception as e:
         print('Error uploading file to Dropbox: ' + str(e))
@@ -104,16 +105,17 @@ def dropbox_upload_file(df, flag=0):
 def uploadanyFile(doc,pdfname,path,flag=0):
     try:
         dbxTeam= ADR_Access_DropboxTeam('admin')
-        
         if flag: #tree = doc
           pdfname=str(pdfname).split('.pdf')[0]+'.xml'
           path=path+pdfname
           f = BytesIO()
-          doc.write(f, encoding='utf-8', xml_declaration=True) 
-          meta=dbxTeam.files_upload(f.getvalue() ,path,mode=dropbox.files.WriteMode("overwrite"))
+          doc.write(f, encoding='utf-8', xml_declaration=True)
+          dbxTeam.files_delete(path) 
+          meta=dbxTeam.files_upload(f.getvalue() ,path)
         else:
            path=path+pdfname
-           meta=dbxTeam.files_upload( doc.write() ,path,mode=dropbox.files.WriteMode("overwrite"))
+           dbxTeam.files_delete(path)
+           meta=dbxTeam.files_upload(doc.write() ,path)
         try:
           shared_link_metadata = dbxTeam.sharing_create_shared_link_with_settings(path)
         except:
@@ -141,28 +143,6 @@ def DropboxItemstoDF(folder_path):
   # print(df2)
   return df2 , files_list
 
-# df2=DropboxItemstoDF()
-
-# Feather format for storing data
-# def ToFeather(df2):
-#   df2.to_feather('df2.feather')
-#   fthr=pd.read_feather('df2.feather')
-#   return fthr
-
-# def GetParquetDF():
-#   # # read the parquet file in current directory, back into a pandas data frame
-#   dbxTeam=ADR_Access_DropboxTeam('user') # or pass dbx in parameters
-#   try:
-#     shared_link_metadata = dbxTeam.sharing_create_shared_link_with_settings( path='/TSA Team Folder/ADR Test/DropboxDirectory/df.parquet.gzip')
-#   except:
-#     shared_link_metadata=dbxTeam.sharing_create_shared_link( path='/TSA Team Folder/ADR Test/DropboxDirectory/df.parquet.gzip')
-#   metadata, res = dbxTeam.sharing_get_shared_link_file(url=shared_link_metadata.url)
-#   data=res.content  # or res.content, or iter_content, or iter_lines, etc. as needed
-
-#   pq_file = io.BytesIO(data)
-#   df = pd.read_parquet(pq_file)
-#   return df
-
 
 def GetParquetDF():
     # Initialize Dropbox client
@@ -191,6 +171,7 @@ def getPathtoPDF_File(nameofPDF):
   try:
     path=parquetDf.loc[parquetDf['name'] == nameofPDF, 'path_display'].iloc[0]
     link=getSharedLink(path)
+    print(path,link)
   except:
     return 'Project does not exist'
   return path,link
@@ -203,33 +184,6 @@ def getPDFData(path):
   data = res.content
   return data
 
-# def retrieveProjects(projname):
-#     print('retrieve')
-    
-#     parquetDf=GetParquetDF()
-#     documentsToMeasure = []
-#     RelevantDocuments = []
-#     projnameWithDetails = f'{projname} 01 Project Details'
-    
-#     # Split the project name into words and convert to lowercase
-#     matches = set(re.findall(r'\b\w+\b', projnameWithDetails.lower()))
-    
-#     # Convert the 'path_display' column to lowercase for case-insensitive matching
-#     parquetDf['path_display_lower'] = parquetDf['path_display'].str.lower()
-    
-#     # Check if all words in matches are present in the path
-#     mask = parquetDf['path_display_lower'].apply(lambda x: all(match in x for match in matches))
-    
-#     # Filter relevant documents
-#     RelevantDocuments = parquetDf.loc[mask, ['name', 'path_display']].values.tolist()
-    
-#     # Filter documents to measure
-#     documentsToMeasure = parquetDf.loc[(mask) & (parquetDf['name'].str.endswith('.pdf')), ['name', 'path_display']].values.tolist()
-    
-#     # Remove the temporary 'path_display_lower' column
-#     parquetDf.drop(columns=['path_display_lower'], inplace=True)
-#     return documentsToMeasure,RelevantDocuments
-
 def retrieveProjects(projname):
   print('retrieve')
 
@@ -252,8 +206,7 @@ def retrieveProjects(projname):
 
   # Remove the temporary 'path_display_lower' column
   parquetDf.drop(columns=['path_display_lower'], inplace=True)
+  print('done')
   return documentsToMeasure,RelevantDocuments
 
 
-
-