Update app.py

app.py

@@ -15,22 +15,26 @@ sentiment_analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncas
 # Function to read content from different file types
 def read_file(file, file_type):
     content = ""
-    if file_type == "docx":
-        doc = Document(file)
-        for para in doc.paragraphs:
-            content += para.text + "\n"
-    elif file_type == "txt":
-        content = file.read().decode("utf-8")
-    elif file_type == "pdf":
-        pdf_reader = PyPDF2.PdfReader(file)
-        for page in pdf_reader.pages:
-            content += page.extract_text() + "\n"
-    elif file_type == "pptx":
-        prs = Presentation(file)
-        for slide in prs.slides:
-            for shape in slide.shapes:
-                if hasattr(shape, "text"):
-                    content += shape.text + "\n"
+    try:
+        if file_type == "docx":
+            doc = Document(file)
+            for para in doc.paragraphs:
+                content += para.text + "\n"
+        elif file_type == "txt":
+            content = file.read().decode("utf-8")
+        elif file_type == "pdf":
+            pdf_reader = PyPDF2.PdfReader(file)
+            for page in pdf_reader.pages:
+                content += page.extract_text() + "\n"
+        elif file_type == "pptx":
+            prs = Presentation(file)
+            for slide in prs.slides:
+                for shape in slide.shapes:
+                    if hasattr(shape, "text"):
+                        content += shape.text + "\n"
+    except Exception as e:
+        content = f"Error reading the file: {str(e)}"
+    
     return content
 
 # Function to process the file and generate outputs
@@ -38,7 +42,7 @@ def process_file(file, file_type, language="en"):
     content = read_file(file, file_type)
     
     # Check if content is not empty
-    if not content.strip():
+    if not content.strip() or "Error" in content:
         return "Error: The document is empty or unsupported format.", None, None, None, None, None
     
     # Summarize the content
@@ -83,7 +87,7 @@ def process_file(file, file_type, language="en"):
 def home_page():
     with gr.Blocks() as home:
         # Header
-        gr.Markdown("## Original Content Rephrased Content")
+        gr.Markdown("## Upload a Document to Process")
 
         # Menu bar as buttons
         with gr.Row():
@@ -93,6 +97,20 @@ def home_page():
         # Display content on home page
         gr.Markdown("Welcome to the Document Processor!")
         gr.Markdown("Upload your document here and click to view details on the 'Full Analysis' page.")
+        
+        # File upload and content output
+        file_input = gr.File(label="Upload Document")
+        content_output = gr.Textbox(label="Original Content")
+        rephrased_output = gr.Textbox(label="Rephrased Content")
+        
+        def on_file_upload(file):
+            if not file:
+                return "No file uploaded.", None
+            content, rephrased, _, _, _, _ = process_file(file, file_type="docx")
+            return content, rephrased
+
+        # Process file on upload
+        file_input.change(on_file_upload, inputs=file_input, outputs=[content_output, rephrased_output])
 
     return home
 
@@ -109,21 +127,18 @@ def detailed_page():
         # File upload and processing components
         file_input = gr.File(label="Upload Document")
         file_type = gr.Dropdown(["pdf", "docx", "txt", "pptx"], label="File Type")
-        content_output = gr.Textbox(label="Original Content")
-        rephrased_output = gr.Textbox(label="Rephrased Content")
-        summary_output = gr.Textbox(label="Summary")
-        sentiment_output = gr.Textbox(label="Sentiment Analysis")
         keywords_output = gr.Textbox(label="Keywords")
+        sentiment_output = gr.Textbox(label="Sentiment Analysis")
         download_link = gr.File(label="Download Processed Document")
         
         def on_file_upload(file, file_type):
             if not file:
-                return "No file uploaded.", None, None, None, None, None
-            content, rephrased, summary, sentiment, keywords, download_path = process_file(file, file_type)
-            return content, rephrased, summary, sentiment, keywords, download_path
+                return "No file uploaded.", None, None, None
+            _, _, _, sentiment, keywords, download_path = process_file(file, file_type)
+            return keywords, sentiment, download_path
 
         # Process file on upload
-        file_input.change(on_file_upload, inputs=[file_input, file_type], outputs=[content_output, rephrased_output, summary_output, sentiment_output, keywords_output, download_link])
+        file_input.change(on_file_upload, inputs=[file_input, file_type], outputs=[keywords_output, sentiment_output, download_link])
 
         # Sample output or content for the detailed analysis page
         gr.Markdown("Here you will see detailed analysis outputs after document upload.")