Update app.py

app.py

@@ -8,13 +8,16 @@ from nltk.tokenize import word_tokenize
 import torch
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
 import time
+import os
+import docx2txt
+import io
+import docx
 
 # Set page title and configuration
 st.set_page_config(
     page_title="Resume-Job Fit Analyzer",
     page_icon="📊",
-    layout="wide",
-    initial_sidebar_state="expanded"
+    layout="wide"
 )
 
 # Download NLTK resources if needed
@@ -49,6 +52,61 @@ def load_models():
     
     return models
 
+# Read resume file
+def read_resume_file(uploaded_file):
+    """Extract text from uploaded resume file"""
+    file_extension = os.path.splitext(uploaded_file.name)[1].lower()
+    
+    if file_extension == ".txt":
+        # Text file
+        text = uploaded_file.read().decode('utf-8')
+        return text
+    
+    elif file_extension == ".docx":
+        # Modern Word document
+        try:
+            text = docx2txt.process(uploaded_file)
+            return text
+        except Exception as e:
+            st.error(f"Error reading DOCX file: {str(e)}")
+            return None
+    
+    elif file_extension == ".doc":
+        # Legacy Word document - this is more complex
+        try:
+            # For .doc files, we'll return a warning that the conversion might not be perfect
+            st.warning("Note: .doc files might not convert perfectly. For best results, upload .docx or .txt files.")
+            
+            # Save the uploaded file temporarily
+            with open("temp_file.doc", "wb") as f:
+                f.write(uploaded_file.getbuffer())
+            
+            # Use an external converter - this is a placeholder
+            # In a real implementation, you might want to use antiword, textract or similar
+            # Here we'll try using docx2txt as a fallback but it might not work well
+            try:
+                text = docx2txt.process("temp_file.doc")
+            except:
+                # If that fails, try a very basic approach
+                with open("temp_file.doc", "rb") as f:
+                    content = f.read()
+                    text = content.decode('utf-8', errors='ignore')
+                    # Try to extract readable text by removing binary parts
+                    text = re.sub(r'[^\x20-\x7E\n\r\t]', '', text)
+            
+            # Clean up
+            if os.path.exists("temp_file.doc"):
+                os.remove("temp_file.doc")
+            
+            return text
+        except Exception as e:
+            st.error(f"Error reading DOC file: {str(e)}")
+            return None
+    
+    else:
+        st.error(f"Unsupported file format: {file_extension}")
+        return None
+
 # Extract skills from text
 def extract_skills(text, skill_keywords):
     """Extract skills from text based on a predefined list of skills"""
@@ -353,28 +411,30 @@ def generate_fallback_assessment(resume_data, job_data, match_scores, fit_status
 st.title("Resume-Job Fit Analyzer")
 st.markdown("### Evaluate how well a resume matches a job description")
 
-# Setup columns for input
-col1, col2 = st.columns(2)
+# Resume upload
+st.subheader("Resume")
+uploaded_file = st.file_uploader("Upload Resume (.doc, .docx, .txt)", type=["doc", "docx", "txt"])
 
-with col1:
-    # Resume input
-    st.subheader("Resume")
-    resume_text = st.text_area("Paste resume text here", height=300, 
-                          placeholder="Paste the candidate's resume text here...")
+# Job description input
+st.subheader("Job Description")
+job_description = st.text_area("Paste job description here", height=200,
+                    placeholder="Paste the job description here...")
 
-with col2:
-    # Job description input
-    st.subheader("Job Description")
-    job_description = st.text_area("Paste job description here", height=300,
-                        placeholder="Paste the job description here...")
+# Display resume text if file is uploaded
+resume_text = None
+if uploaded_file is not None:
+    resume_text = read_resume_file(uploaded_file)
+    if resume_text:
+        with st.expander("View Resume Text"):
+            st.text(resume_text[:1000] + ("..." if len(resume_text) > 1000 else ""))
 
 # Analysis button
-analyze_button = st.button("Analyze Match", type="primary", use_container_width=True)
+analyze_button = st.button("Analyze Match", type="primary")
 
 # Main analysis logic
 if analyze_button:
     if not resume_text or not job_description:
-        st.error("Please provide both a resume and a job description.")
+        st.error("Please upload a resume file and provide a job description.")
     else:
         with st.spinner("Analyzing resume and job match..."):
             # Record start time