utils/cv_processor.py

from PyPDF2 import PdfReader
from docx import Document
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import re
import numpy as np
import os

class CVProcessor:
    def __init__(self):
        self.model = SentenceTransformer('all-MiniLM-L6-v2')
        self.job_reqs = self._load_job_requirements()
    
    def extract_text(self, file_path):
        if file_path.endswith('.pdf'):
            reader = PdfReader(file_path)
            return " ".join([page.extract_text() for page in reader.pages])
        elif file_path.endswith('.docx'):
            doc = Document(file_path)
            return " ".join([para.text for para in doc.paragraphs])
    
    def evaluate(self, cv_path, job_role):
        cv_text = self.extract_text(cv_path)
        reqs = self.job_reqs[job_role]
        
        # Semantic similarity
        cv_embed = self.model.encode(cv_text)
        req_embed = self.model.encode(reqs["required_skills"])
        similarity = cosine_similarity([cv_embed], [req_embed])[0][0]
        
        # Experience check
        exp_matches = re.findall(r"(\d+)\s+years?", cv_text.lower())
        total_exp = sum(int(m) for m in exp_matches) if exp_matches else 0
        
        is_qualified = (similarity > 0.4 and 
                       total_exp >= reqs["min_experience"])
        
        return {
            "is_qualified": is_qualified,
            "cv_summary": {
                "text": cv_text[:2000] + "..." if len(cv_text) > 2000 else cv_text,
                "experience": total_exp,
                "skills_match": float(similarity)
            }
        }
    
    def _load_job_requirements(self):
        return {
            "Software Engineer": {
                "min_experience": 2,
                "required_skills": "programming, algorithms, software development, testing, debugging"
            },
            "Data Scientist": {
                "min_experience": 3,
                "required_skills": "machine learning, statistics, python, data analysis, SQL"
            }
        }