backend/modules/parser.py

import os
import re
import pdfplumber
import docx2txt
import spacy
from typing import List, Dict, Optional
import pprint 

# Load NLP model
try:
    nlp = spacy.load("en_core_web_sm")
except OSError:
    print("SpaCy model 'en_core_web_sm' not found.")
    print("Please run: python -m spacy download en_core_web_sm")
    exit()

# Text Extraction
def extract_text_from_pdf(file_path: str) -> str:
    """Extract text from PDF with proper page separation"""
    text = ""
    try:
        with pdfplumber.open(file_path) as pdf:
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n"
    except Exception as e:
        print(f"Error reading PDF file {file_path}: {e}")
    return text

def extract_text_from_docx(file_path: str) -> str:
    """Extract text from DOCX while preserving structure"""
    try:
        return docx2txt.process(file_path)
    except Exception as e:
        print(f"Error reading DOCX file {file_path}: {e}")
        return ""

def clean_text(text: str) -> str:
    """Normalize whitespace and clean artifacts"""
    text = re.sub(r'\n+', '\n', text)  # Collapse multiple newlines
    text = re.sub(r'[^\S\n]+', ' ', text)  # Collapse multiple spaces/tabs
    return text.strip()

def validate_email(email: str) -> bool:
    """Validate email format strictly"""
    if not email:
        return False
    
    # Check for invalid characters
    if any(char in email for char in ['|', '\n', '\t', ' ', ',', ';']):
        return False
    
    # Standard email regex
    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
    return bool(re.match(pattern, email))

def validate_phone(phone: str) -> bool:
    """Validate phone number format"""
    if not phone:
        return False
    
    # Remove common formatting characters
    cleaned = re.sub(r'[\s\-\(\)]+', '', phone)
    
    # Check if it's a reasonable phone number (7-15 digits)
    return bool(re.match(r'^\+?\d{7,15}$', cleaned))

# Entity Extraction
def extract_entities(text: str) -> Dict[str, Optional[str]]:
    """
    Extract name, email, and phone with robust validation
    Returns: {'name': str, 'email': str, 'phone': str}
    """
    # Extract name from first 3 lines (where it usually appears)
    first_lines = '\n'.join(text.split('\n')[:3])
    doc = nlp(first_lines)
    name = ""
    
    # Try to find PERSON entity
    for ent in doc.ents:
        if ent.label_ == "PERSON":
            # Clean the name - take only the first line and remove extra whitespace
            potential_name = ent.text.split('\n')[0].strip()
            potential_name = re.sub(r'\s+', ' ', potential_name)
            
            # Validate name (should not contain numbers or special chars except spaces, hyphens, apostrophes)
            if re.match(r"^[A-Za-z\s\-'\.]+$", potential_name) and len(potential_name) > 2:
                name = potential_name
                break
    
    # Fallback: Use first line if no PERSON entity found
    if not name:
        first_line = text.split('\n')[0].strip()
        # Clean and validate
        first_line = re.sub(r'\s+', ' ', first_line)
        if re.match(r"^[A-Za-z\s\-'\.]+$", first_line) and len(first_line) > 2:
            name = first_line
    
    # Extract email with strict validation
    email = None
    # Find all potential emails
    email_pattern = r'\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b'
    email_matches = re.findall(email_pattern, text)
    
    # Validate and pick the first valid one
    for match in email_matches:
        # Clean the match (remove any trailing/leading dots or special chars)
        cleaned_email = match.strip().lower()
        if validate_email(cleaned_email):
            email = cleaned_email
            break
    
    # Extract phone with validation
    phone = None
    # Multiple phone patterns
    phone_patterns = [
        r'\+?\d{1,3}[\s\-]?\(?\d{3}\)?[\s\-]?\d{3}[\s\-]?\d{4}',  # US/International
        r'\+?\d{10,15}',  # Simple international
        r'\(?\d{3}\)?[\s\-]?\d{3}[\s\-]?\d{4}',  # US format
    ]
    
    for pattern in phone_patterns:
        phone_match = re.search(pattern, text)
        if phone_match:
            potential_phone = phone_match.group(0).strip()
            if validate_phone(potential_phone):
                phone = potential_phone
                break
    
    return {
        "name": name if name else None,
        "email": email,
        "phone": phone
    }

# Skills Extraction
def extract_skills(text: str, skill_list: List[str]) -> List[str]:
    """Find skills using case-insensitive whole-word matching"""
    found_skills = set()
    text_lower = text.lower()
    
    for skill in skill_list:
        # Match whole words to avoid partial matches
        pattern = rf'\b{re.escape(skill.lower())}\b'
        if re.search(pattern, text_lower):
            found_skills.add(skill)
    
    return sorted(found_skills)

# Education Extraction
def extract_education(text: str) -> List[str]:
    """Extract education degrees with flexible matching"""
    patterns = [
        r"(?:B\.?Tech|Bachelor[\s']*(?:of|in)?[\s']*Technology)\b.*?(?:Computer Science|Artificial Intelligence|IT|\bAI\b|\bCS\b|Information Technology)",
        r"(?:M\.?Tech|Master[\s']*(?:of|in)?[\s']*Technology)\b.*?(?:Data Science|Machine Learning|Computer)",
        r"B\.?[Ee]\.?\b.*?(?:Computer|Electrical|Electronics)",
        r"B\.?[Ss]c\.?\b.*?(?:Computer|Physics|Mathematics|IT)",
        r"\bPhD\b.*?(?:Computer Science|Engineering|Technology)",
        r"(?:Bachelor|Master).*?(?:Computer Science|Information Technology|Software Engineering)",
        r"(?:B\.?A\.|Bachelor of Arts).*?(?:Computer|Technology)",
        r"(?:M\.?S\.|Master of Science).*?(?:Computer|Data|Technology)"
    ]
    
    found = set()
    for pattern in patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        for match in matches:
            # Clean the match
            cleaned = re.sub(r'\s+', ' ', match.strip())
            if len(cleaned) > 5:  # Reasonable length
                found.add(cleaned)
    
    return sorted(found) if found else []

# Experience Extraction
def calculate_experience_years(experience_dates: List[str]) -> float:
    """Calculate total years of experience from date ranges"""
    total_years = 0.0
    
    for date_range in experience_dates:
        # Find all 4-digit years in the string
        years = list(map(int, re.findall(r'\b(19|20)\d{2}\b', date_range)))
        
        # Handle "YYYY-YYYY" or "Month YYYY - Month YYYY"
        if len(years) >= 2:
            start_year = min(years)
            end_year = max(years)
            total_years += (end_year - start_year)
    
    return round(total_years, 1)

def extract_experience_dates(text: str) -> List[str]:
    """Extract all experience date ranges"""
    patterns = [
        r'\b(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]*\s+(19|20)\d{2}\s*[\-–to]+\s*(?:(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]*\s+)?(19|20)\d{2}|Present|Current',
        r'\b(19|20)\d{2}\s*[\-–to]+\s*(19|20)\d{2}\b',
        r'\b(19|20)\d{2}\s*[\-–to]+\s*(?:Present|Current)\b'
    ]
    matches = []
    for pattern in patterns:
        matches.extend(re.findall(pattern, text, re.IGNORECASE))
    
    # Convert tuples to strings
    return [' '.join(m) if isinstance(m, tuple) else m for m in matches]

# Main Parser
def parse_resume(file_path: str) -> Optional[Dict]:
    """Parse resume and return structured data with robust validation"""
    if not os.path.exists(file_path):
        print(f"Error: File not found at {file_path}")
        return None

    # Extract text based on file type
    if file_path.endswith(".pdf"):
        text = extract_text_from_pdf(file_path)
    elif file_path.endswith(".docx"):
        text = extract_text_from_docx(file_path)
    else:
        print("Error: Only PDF and DOCX files are supported")
        return None
    
    if not text or len(text.strip()) < 50:
        print("Could not extract sufficient text from the file.")
        return None

    text = clean_text(text)
    
    # Define comprehensive skills list
    skills_list = [
        # Programming Languages
        "Python", "Java", "JavaScript", "TypeScript", "C++", "C#", "Ruby", "Go", "Rust",
        "PHP", "Swift", "Kotlin", "Scala", "R", "MATLAB", "Perl",
        
        # Web Technologies
        "HTML", "CSS", "React", "Angular", "Vue.js", "Node.js", "Express", "Django",
        "Flask", "FastAPI", "Spring Boot", "ASP.NET", "jQuery", "Bootstrap", "Tailwind",
        
        # Databases
        "SQL", "MySQL", "PostgreSQL", "MongoDB", "Redis", "Cassandra", "Oracle",
        "SQL Server", "SQLite", "DynamoDB", "Elasticsearch",
        
        # Cloud & DevOps
        "AWS", "Azure", "Google Cloud", "GCP", "Docker", "Kubernetes", "Jenkins",
        "Git", "GitHub", "GitLab", "CI/CD", "Terraform", "Ansible",
        
        # Data Science & ML
        "Machine Learning", "Deep Learning", "TensorFlow", "PyTorch", "Keras",
        "Scikit-learn", "Pandas", "NumPy", "Matplotlib", "Seaborn", "NLP",
        "Natural Language Processing", "Computer Vision", "Data Analysis",
        "Big Data", "Spark", "Hadoop", "Tableau", "Power BI",
        
        # Other Tools
        "Linux", "Unix", "Bash", "PowerShell", "Agile", "Scrum", "JIRA",
        "Confluence", "Postman", "REST API", "GraphQL", "Microservices"
    ]
    
    # Extract all information
    entities = extract_entities(text)
    experience_dates = extract_experience_dates(text)
    
    result = {
        "name": entities.get("name"),
        "email": entities.get("email"),
        "phone": entities.get("phone"),
        "education": extract_education(text),
        "total_experience_years": calculate_experience_years(experience_dates),
        "skills": extract_skills(text, skills_list),
        "full_text": text[:5000]  # Limit to first 5000 chars
    }
    
    # Validate critical fields
    if not result["name"]:
        result["name"] = "Unknown Candidate"
    
    if not result["email"]:
        print("Warning: No valid email found in resume")
    
    return result

# --- Main Execution ---
if __name__ == "__main__":
    # Test with a file
    file_path = "test_resume.pdf"  # Change this to your test file
    
    if os.path.exists(file_path):
        parsed_data = parse_resume(file_path)
        
        if parsed_data:
            print("--- Resume Parsing Complete ---")
            pprint.pprint(parsed_data)
            print("-----------------------------")
    else:
        print(f"Test file not found: {file_path}")
        print("Please provide a test resume file to parse.")