Update tsadropboxretrieval.py

tsadropboxretrieval.py

@@ -201,20 +201,16 @@ def getPDFData(path):
   return data
 
 def retrieveProjects(projname):
-  print('retrieve')
-
+  projname='/'+projname.split(' ')[0]
   parquetDf=GetParquetDF()
   documentsToMeasure = []
   RelevantDocuments = []
   projnameWithDetails = f'{projname} 01 Project Details'
-  # Split the project name into words and convert to lowercase
-  matches = set(re.split(r'[`\-= ~!@#$%^&*()_+\[\]{};\'\\:"|<,/<>?]', projnameWithDetails.lower()))
-
-  # Convert the 'path_display' column to lowercase for case-insensitive matching
+    
   parquetDf['path_display_lower'] = parquetDf['path_display'].str.lower()
 
-  # Create a mask to filter relevant documents
-  mask = parquetDf['path_display_lower'].apply(lambda x: all(match in x for match in matches))
+  # Filter based on the presence of '/2221' and '01 Project Details'
+  mask = parquetDf['path_display_lower'].apply(lambda x: projname in x and '01 project details' in x)
 
   # Filter RelevantDocuments and documentsToMeasure using the mask
   RelevantDocuments = parquetDf[mask][['name', 'path_display']].values.tolist()