Update app.py

app.py

@@ -214,13 +214,152 @@ def extract_skills(text, summary):
     else:
         return "No specific technical skills clearly identified (review resume for details)"
 
+def extract_work_experience(text):
+    """Extract work experience from resume"""
+    # Common section headers for work experience
+    work_headers = [
+        "work experience", "professional experience", "employment history", 
+        "work history", "experience", "professional background", "career history"
+    ]
+    
+    # Common section headers that might come after work experience
+    next_section_headers = [
+        "education", "skills", "certifications", "projects", "achievements",
+        "languages", "interests", "references", "additional information"
+    ]
+    
+    text_lower = text.lower()
+    lines = text.split('\n')
+    
+    # Find the start of work experience section
+    work_start_idx = -1
+    work_header_used = ""
+    
+    for idx, line in enumerate(lines):
+        line_lower = line.lower().strip()
+        if any(header in line_lower for header in work_headers):
+            if any(header == line_lower or header + ":" == line_lower for header in work_headers):
+                work_start_idx = idx
+                work_header_used = line.strip()
+                break
+    
+    if work_start_idx == -1:
+        # Try to find work experience by looking for date patterns (common in resumes)
+        date_pattern = r'(19|20)\d{2}\s*(-|–|to)\s*(19|20)\d{2}|present|current|now'
+        for idx, line in enumerate(lines):
+            if re.search(date_pattern, line.lower()):
+                # Check surrounding lines for job titles or company names
+                context = " ".join(lines[max(0, idx-2):min(len(lines), idx+3)])
+                if any(title.lower() in context.lower() for title in ["manager", "developer", "engineer", "analyst", "assistant", "director", "coordinator"]):
+                    work_start_idx = max(0, idx-2)
+                    break
+    
+    if work_start_idx == -1:
+        return "No clear work experience section found"
+    
+    # Find the end of work experience section
+    work_end_idx = len(lines)
+    for idx in range(work_start_idx + 1, len(lines)):
+        line_lower = lines[idx].lower().strip()
+        if any(header in line_lower for header in next_section_headers):
+            if any(header == line_lower or header + ":" == line_lower for header in next_section_headers):
+                work_end_idx = idx
+                break
+    
+    # Extract the work experience section
+    work_section = lines[work_start_idx + 1:work_end_idx]
+    
+    # Process the work experience to make it more concise
+    # Look for companies, positions, dates, and key responsibilities
+    companies = []
+    current_company = {"name": "", "position": "", "dates": "", "description": []}
+    
+    for line in work_section:
+        line = line.strip()
+        if not line:
+            continue
+            
+        # Check if this is likely a new company/position entry
+        if re.search(r'(19|20)\d{2}\s*(-|–|to)\s*(19|20)\d{2}|present|current|now', line.lower()):
+            # Save previous company if it exists
+            if current_company["name"] or current_company["position"]:
+                companies.append(current_company)
+                current_company = {"name": "", "position": "", "dates": "", "description": []}
+            
+            # This line likely contains position/company and dates
+            current_company["dates"] = line
+            
+            # Try to extract position and company
+            parts = re.split(r'(19|20)\d{2}', line, 1)
+            if len(parts) > 1:
+                current_company["position"] = parts[0].strip()
+        elif current_company["dates"] and not current_company["name"]:
+            # This line might be the company name or the continuation of position details
+            current_company["name"] = line
+        else:
+            # This is likely a responsibility or detail
+            current_company["description"].append(line)
+    
+    # Add the last company if it exists
+    if current_company["name"] or current_company["position"]:
+        companies.append(current_company)
+    
+    # Format the work experience
+    if not companies:
+        # Try a different approach - just extract text blocks that might be jobs
+        job_blocks = []
+        current_block = []
+        
+        for line in work_section:
+            line = line.strip()
+            if not line:
+                if current_block:
+                    job_blocks.append(" ".join(current_block))
+                    current_block = []
+            else:
+                current_block.append(line)
+        
+        if current_block:
+            job_blocks.append(" ".join(current_block))
+        
+        if job_blocks:
+            return "\n• " + "\n• ".join(job_blocks[:3])  # Limit to top 3 entries
+        else:
+            return "Work experience information could not be clearly structured"
+    
+    # Format the companies into a readable output
+    formatted_experience = []
+    for company in companies[:3]:  # Limit to top 3 most recent positions
+        entry = []
+        if company["position"]:
+            entry.append(f"**{company['position']}**")
+        if company["name"]:
+            entry.append(f"at {company['name']}")
+        if company["dates"]:
+            entry.append(f"({company['dates']})")
+        
+        position_line = " ".join(entry)
+        
+        if company["description"]:
+            # Limit to first 2-3 bullet points for conciseness
+            description = company["description"][:3]
+            description_text = "; ".join(description)
+            formatted_experience.append(f"{position_line} - {description_text}")
+        else:
+            formatted_experience.append(position_line)
+    
+    if formatted_experience:
+        return "\n• " + "\n• ".join(formatted_experience)
+    else:
+        return "Work experience information could not be clearly structured"
+
 #####################################
 # Function: Summarize Resume Text
 #####################################
 def summarize_resume_text(resume_text, models):
     """
     Generates a structured summary of the resume text including name, age, 
-    expected job industry, and skills of the candidate.
+    expected job industry, skills, and work experience of the candidate.
     """
     start_time = time.time()
     
@@ -246,11 +385,13 @@ def summarize_resume_text(resume_text, models):
     age = extract_age(resume_text)
     industry = extract_industry(resume_text, base_summary)
     skills = extract_skills(resume_text, base_summary)
+    work_experience = extract_work_experience(resume_text)
     
     # Format the structured summary
     formatted_summary = f"Name: {name}\n"
     formatted_summary += f"Age: {age}\n"
-    formatted_summary += f"Expected Job Industry: {industry}\n"
+    formatted_summary += f"Expected Job Industry: {industry}\n\n"
+    formatted_summary += f"Previous Work Experience: {work_experience}\n\n"
     formatted_summary += f"Skills: {skills}"
     
     execution_time = time.time() - start_time
@@ -292,7 +433,7 @@ st.markdown(
     """
 Upload your resume file in **.docx**, **.doc**, or **.txt** format. The app performs the following tasks:
 1. Extracts text from the resume.
-2. Uses AI to generate a structured candidate summary with name, age, expected job industry, and skills.
+2. Uses AI to generate a structured candidate summary with name, age, expected job industry, previous work experience, and skills.
 3. Compares the candidate summary with a company profile to produce a suitability score.
 """
 )