Update app.py

app.py

@@ -5,8 +5,6 @@ import datetime
 import dotenv
 import pandas as pd
 import streamlit as st
-import streamlit.components.v1 as components
-from annotated_text import annotated_text
 from streamlit_tags import st_tags
 from PyPDF2 import PdfReader, PdfWriter
 from presidio_helpers import (
@@ -53,7 +51,7 @@ st_model_package = st_model.split("/")[0]
 st_model = st_model if st_model_package.lower() not in ("spacy", "huggingface") else "/".join(st_model.split("/")[1:])
 
 analyzer_params = (st_model_package, st_model)
-st.sidebar.warning("Note: Models might take some time to download.")
+st.sidebar.warning("Note: Models might take some time to download on first run.")
 
 st_operator = st.sidebar.selectbox(
     "De-identification approach",
@@ -87,80 +85,101 @@ with col1:
     uploaded_file = st.file_uploader("Upload PDF", type=["pdf"])
     
     if uploaded_file:
-        # Read PDF
-        pdf_reader = PdfReader(uploaded_file)
-        text = ""
-        for page in pdf_reader.pages:
-            text += page.extract_text() + "\n"
-
-        # Analyze
-        analyzer = analyzer_engine(*analyzer_params)
-        st_analyze_results = analyze(
-            analyzer=analyzer,
-            text=text,
-            entities=get_supported_entities(*analyzer_params),
-            language="en",
-            score_threshold=st_threshold,
-            return_decision_process=st_return_decision_process,
-            allow_list=st_allow_list,
-            deny_list=st_deny_list,
-        )
-
-        # Process results
-        phi_types = set(res.entity_type for res in st_analyze_results)
-        if phi_types:
-            st.success(f"Removed PHI types: {', '.join(phi_types)}")
-        else:
-            st.info("No PHI detected")
-
-        # Anonymize
-        anonymized_result = anonymize(
-            text=text,
-            operator=st_operator,
-            analyze_results=st_analyze_results,
-        )
-
-        # Create new PDF
-        pdf_writer = PdfWriter()
-        for page in pdf_reader.pages:
-            pdf_writer.add_page(page)
-
-        # Generate output filename with timestamp
-        timestamp = datetime.datetime.now().strftime("%I%M%p_%d-%m-%y")
-        output_filename = f"{timestamp}_{uploaded_file.name}"
-        
-        # Save modified PDF
-        with open(output_filename, "wb") as f:
-            pdf_writer.write(f)
-
-        # Generate base64 download link
-        with open(output_filename, "rb") as f:
-            pdf_bytes = f.read()
-            b64 = base64.b64encode(pdf_bytes).decode()
-            href = f'<a href="data:application/pdf;base64,{b64}" download="{output_filename}">Download de-identified PDF</a>'
-            st.markdown(href, unsafe_allow_html=True)
-
-        # Display findings
-        with col2:
-            st.subheader("Findings")
-            if st_analyze_results:
-                df = pd.DataFrame.from_records([r.to_dict() for r in st_analyze_results])
-                df["text"] = [text[res.start:res.end] for res in st_analyze_results]
-                df_subset = df[["entity_type", "text", "start", "end", "score"]].rename(
-                    {
-                        "entity_type": "Entity type",
-                        "text": "Text",
-                        "start": "Start",
-                        "end": "End",
-                        "score": "Confidence",
-                    },
-                    axis=1,
-                )
-                if st_return_decision_process:
-                    analysis_explanation_df = pd.DataFrame.from_records(
-                        [r.analysis_explanation.to_dict() for r in st_analyze_results]
-                    )
-                    df_subset = pd.concat([df_subset, analysis_explanation_df], axis=1)
-                st.dataframe(df_subset.reset_index(drop=True), use_container_width=True)
+        try:
+            # Read PDF
+            pdf_reader = PdfReader(uploaded_file)
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text() + "\n"
+
+            # Initialize analyzer
+            try:
+                analyzer = analyzer_engine(*analyzer_params)
+            except Exception as e:
+                st.error(f"Failed to load model: {str(e)}")
+                st.info("Ensure models are downloaded (e.g., 'python -m spacy download en_core_web_lg') and check network/permissions.")
+                raise
+
+            # Analyze
+            st_analyze_results = analyze(
+                analyzer=analyzer,
+                text=text,
+                entities=get_supported_entities(*analyzer_params),
+                language="en",
+                score_threshold=st_threshold,
+                return_decision_process=st_return_decision_process,
+                allow_list=st_allow_list,
+                deny_list=st_deny_list,
+            )
+
+            # Process results
+            phi_types = set(res.entity_type for res in st_analyze_results)
+            if phi_types:
+                st.success(f"Removed PHI types: {', '.join(phi_types)}")
             else:
-                st.text("No findings")
+                st.info("No PHI detected")
+
+            # Anonymize
+            anonymized_result = anonymize(
+                text=text,
+                operator=st_operator,
+                analyze_results=st_analyze_results,
+            )
+
+            # Create new PDF
+            pdf_writer = PdfWriter()
+            for page in pdf_reader.pages:
+                pdf_writer.add_page(page)
+
+            # Generate output filename with timestamp
+            timestamp = datetime.datetime.now().strftime("%I%M%p_%d-%m-%y")
+            output_filename = f"{timestamp}_{uploaded_file.name}"
+            
+            # Save modified PDF
+            try:
+                with open(output_filename, "wb") as f:
+                    pdf_writer.write(f)
+            except PermissionError as e:
+                st.error(f"Permission denied when saving PDF: {str(e)}")
+                st.info("Check write permissions in the current directory.")
+                raise
+
+            # Generate base64 download link
+            try:
+                with open(output_filename, "rb") as f:
+                    pdf_bytes = f.read()
+                    b64 = base64.b64encode(pdf_bytes).decode()
+                    href = f'<a href="data:application/pdf;base64,{b64}" download="{output_filename}">Download de-identified PDF</a>'
+                    st.markdown(href, unsafe_allow_html=True)
+            except Exception as e:
+                st.error(f"Error generating download link: {str(e)}")
+                raise
+
+            # Display findings
+            with col2:
+                st.subheader("Findings")
+                if st_analyze_results:
+                    df = pd.DataFrame.from_records([r.to_dict() for r in st_analyze_results])
+                    df["text"] = [text[res.start:res.end] for res in st_analyze_results]
+                    df_subset = df[["entity_type", "text", "start", "end", "score"]].rename(
+                        {
+                            "entity_type": "Entity type",
+                            "text": "Text",
+                            "start": "Start",
+                            "end": "End",
+                            "score": "Confidence",
+                        },
+                        axis=1,
+                    )
+                    if st_return_decision_process:
+                        analysis_explanation_df = pd.DataFrame.from_records(
+                            [r.analysis_explanation.to_dict() for r in st_analyze_results]
+                        )
+                        df_subset = pd.concat([df_subset, analysis_explanation_df], axis=1)
+                    st.dataframe(df_subset.reset_index(drop=True), use_container_width=True)
+                else:
+                    st.text("No findings")
+
+        except Exception as e:
+            st.error(f"An error occurred: {str(e)}")
+            logger.error(f"Processing error: {str(e)}")