Add comprehensive upload debugging and 4-method file reading

app.py

@@ -55,7 +55,7 @@ if 'uploaded_data_df' not in st.session_state:
 if 'last_uploaded_file' not in st.session_state:
     st.session_state.last_uploaded_file = None
 
-# Enhanced file upload processing
+# Enhanced file upload processing with comprehensive error handling
 if uploaded_file is not None:
     # Check if this is a new file
     file_id = f"{uploaded_file.name}_{uploaded_file.size}"
@@ -65,29 +65,62 @@ if uploaded_file is not None:
     
     # Only process if it's a new file
     if st.session_state.current_file_id != file_id:
+        st.sidebar.info("🔄 Processing uploaded file...")
+        
+        # Try multiple methods to read the file
+        df = None
+        success_method = None
+        
+        # Method 1: Direct pandas read
         try:
-            st.sidebar.info("🔄 Processing uploaded file...")
+            df = pd.read_csv(uploaded_file)
+            success_method = "Direct Read"
+        except Exception as e1:
+            st.sidebar.warning(f"Method 1 failed: {str(e1)[:50]}...")
             
-            # Try reading the file with different methods
+            # Method 2: Read as bytes
             try:
-                # Method 1: Direct read
-                df = pd.read_csv(uploaded_file)
-            except:
-                # Method 2: Read as bytes then convert
+                uploaded_file.seek(0)  # Reset file pointer
                 bytes_data = uploaded_file.getvalue()
-                df = pd.read_csv(io.BytesIO(bytes_data))
-            
-            # Store in session state
+                df = pd.read_csv(BytesIO(bytes_data))
+                success_method = "Bytes Read"
+            except Exception as e2:
+                st.sidebar.warning(f"Method 2 failed: {str(e2)[:50]}...")
+                
+                # Method 3: Read as string
+                try:
+                    uploaded_file.seek(0)  # Reset file pointer
+                    string_data = uploaded_file.getvalue().decode("utf-8")
+                    df = pd.read_csv(io.StringIO(string_data))
+                    success_method = "String Read"
+                except Exception as e3:
+                    st.sidebar.error(f"Method 3 failed: {str(e3)[:50]}...")
+                    
+                    # Method 4: Force UTF-8 encoding
+                    try:
+                        uploaded_file.seek(0)
+                        raw_data = uploaded_file.read()
+                        if isinstance(raw_data, bytes):
+                            string_data = raw_data.decode('utf-8')
+                        else:
+                            string_data = raw_data
+                        df = pd.read_csv(io.StringIO(string_data))
+                        success_method = "Force UTF-8"
+                    except Exception as e4:
+                        st.sidebar.error(f"All methods failed. Last error: {str(e4)}")
+        
+        # If successful, store the data
+        if df is not None:
             st.session_state.uploaded_data_df = df
             st.session_state.last_uploaded_file = uploaded_file.name
             st.session_state.current_file_id = file_id
             
             st.sidebar.success(f"✅ **File loaded successfully!**")
             st.sidebar.success(f"📁 **{uploaded_file.name}** ({len(df)} rows, {len(df.columns)} columns)")
-            
-        except Exception as e:
-            st.sidebar.error(f"❌ **Error reading file:** {str(e)}")
-            st.sidebar.info("💡 Try the 'Process Uploaded File' button below")
+            st.sidebar.info(f"🔧 Used method: {success_method}")
+        else:
+            st.sidebar.error("❌ **All reading methods failed!**")
+            st.sidebar.info("💡 Try the manual processing button below or paste your data")
             st.session_state.uploaded_data_df = None
     else:
         # File already processed

debug_upload.py

@@ -0,0 +1,93 @@
+import streamlit as st
+import pandas as pd
+import io
+import traceback
+
+st.set_page_config(page_title="Upload Debug Tool", layout="wide")
+st.title("🔧 File Upload Debug Tool")
+
+st.markdown("""
+This tool will help us diagnose the exact upload issue.
+""")
+
+# Initialize session state
+if 'debug_info' not in st.session_state:
+    st.session_state.debug_info = []
+
+def log_debug(message):
+    st.session_state.debug_info.append(message)
+    st.write(f"DEBUG: {message}")
+
+st.sidebar.header("Upload Test")
+
+# Simple file uploader
+uploaded_file = st.sidebar.file_uploader(
+    "Test File Upload",
+    type=["csv"],
+    key="debug_uploader"
+)
+
+if uploaded_file is not None:
+    log_debug(f"File detected: {uploaded_file.name}")
+    log_debug(f"File size: {uploaded_file.size} bytes")
+    log_debug(f"File type: {uploaded_file.type}")
+    
+    try:
+        # Test method 1: Direct read
+        log_debug("Attempting Method 1: Direct pd.read_csv()")
+        df1 = pd.read_csv(uploaded_file)
+        log_debug(f"SUCCESS Method 1: {len(df1)} rows, {len(df1.columns)} columns")
+        st.success("✅ Method 1 (Direct read) WORKED!")
+        st.dataframe(df1.head())
+        
+    except Exception as e:
+        log_debug(f"FAILED Method 1: {str(e)}")
+        st.error(f"❌ Method 1 failed: {str(e)}")
+        
+        try:
+            # Test method 2: Reset and read as bytes
+            log_debug("Attempting Method 2: Read as bytes")
+            uploaded_file.seek(0)  # Reset file pointer
+            bytes_data = uploaded_file.getvalue()
+            log_debug(f"Bytes data length: {len(bytes_data)}")
+            df2 = pd.read_csv(io.BytesIO(bytes_data))
+            log_debug(f"SUCCESS Method 2: {len(df2)} rows, {len(df2.columns)} columns")
+            st.success("✅ Method 2 (Bytes read) WORKED!")
+            st.dataframe(df2.head())
+            
+        except Exception as e2:
+            log_debug(f"FAILED Method 2: {str(e2)}")
+            st.error(f"❌ Method 2 failed: {str(e2)}")
+            
+            try:
+                # Test method 3: Read as string
+                log_debug("Attempting Method 3: Read as string")
+                uploaded_file.seek(0)
+                string_data = uploaded_file.getvalue().decode("utf-8")
+                log_debug(f"String data length: {len(string_data)}")
+                df3 = pd.read_csv(io.StringIO(string_data))
+                log_debug(f"SUCCESS Method 3: {len(df3)} rows, {len(df3.columns)} columns")
+                st.success("✅ Method 3 (String read) WORKED!")
+                st.dataframe(df3.head())
+                
+            except Exception as e3:
+                log_debug(f"FAILED Method 3: {str(e3)}")
+                st.error(f"❌ Method 3 failed: {str(e3)}")
+                st.error("❌ ALL METHODS FAILED!")
+                
+                # Show full traceback
+                st.code(traceback.format_exc())
+
+else:
+    st.info("👆 Upload a CSV file to test different reading methods")
+
+# Show debug log
+if st.session_state.debug_info:
+    st.markdown("### Debug Log")
+    for i, msg in enumerate(st.session_state.debug_info):
+        st.text(f"{i+1}. {msg}")
+
+# Clear debug log
+if st.button("Clear Debug Log"):
+    st.session_state.debug_info = []
+    st.rerun()