Create pdfDocumentProcessor.py

pdfDocumentProcessor.py

@@ -0,0 +1,57 @@
+import streamlit as st
+import os
+import pandas as pd
+import base64
+from findUpdate import FindUpdate  # Import the FindUpdate class
+from tempfile import NamedTemporaryFile
+
+class PDFDocumentProcessor:
+    def __init__(self):
+        self.uploaded_agreement = None
+        self.uploaded_template = None
+        self.find_update = FindUpdate()  # Create an instance of FindUpdate class
+
+    def file_uploaders(self):
+        """Function to handle file uploads."""
+        self.uploaded_agreement = st.file_uploader("Upload the PDF Agreement", type=['pdf'])
+        self.uploaded_template = st.file_uploader("Upload the PDF Template", type=['pdf'])
+
+    def process_files(self, agreement_path, template_path):
+        """Main file processing logic."""
+        try:
+            # Use the find_update instance to call the processing function
+            result = self.find_update.main_processing_function(agreement_path, template_path)
+            st.success("Files successfully processed!")
+
+            # Convert the result dictionary to a DataFrame
+            df_changes = pd.DataFrame(result['changes'])
+            df_changes = df_changes[['section_number', 'page_number', 'actual', 'changed', 'analysis', 'type_of_change']]
+
+            # Display the DataFrame in the UI
+            st.dataframe(df_changes, height=600)  # You can adjust height based on your needs
+
+            # Convert DataFrame to CSV for download
+            csv = df_changes.to_csv(index=False)
+            b64 = base64.b64encode(csv.encode()).decode()  # some browsers need base64 encoding
+            # href = f'<a href="data:file/csv;base64,{b64}" download="document_changes.csv">Download CSV File</a>'
+            st.markdown(href, unsafe_allow_html=True)
+
+        except Exception as e:
+            st.error(f"Error processing files: {e}")
+        finally:
+            # Clean up temporary files after processing
+            os.remove(agreement_path)
+            os.remove(template_path)
+
+    def save_uploaded_files(self):
+        """Save the uploaded files temporarily for processing."""
+        if self.uploaded_agreement and self.uploaded_template:
+            with NamedTemporaryFile(delete=False, suffix=".pdf", mode='wb') as temp_agreement:
+                temp_agreement.write(self.uploaded_agreement.read())
+                agreement_path = temp_agreement.name
+
+            with NamedTemporaryFile(delete=False, suffix=".pdf", mode='wb') as temp_template:
+                temp_template.write(self.uploaded_template.read())
+                template_path = temp_template.name
+
+            self.process_files(agreement_path, template_path)