checker.py

import os
import PyPDF2
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from const import position_map, BASE_FOLDER, USER_RESUME_NAME
from colorama import Fore, Style, init

# Initialize colorama
init(autoreset=True)

def extract_text_from_pdf(file_path):
    """Extract text from a PDF file."""
    with open(file_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        text = ''
        for page in reader.pages:
            text += page.extract_text() + ' '
    return text.strip().lower()

def rank_resumes(cv_folder, keywords):
    """Rank resumes based on keyword relevance."""
    resumes = []
    resume_names = []

    # Convert keywords to lowercase
    keywords_lower = [keyword.lower() for keyword in keywords]
    
    # Read all PDF files in the CV folder
    for filename in os.listdir(cv_folder):
        if filename.endswith('.pdf'):
            file_path = os.path.join(cv_folder, filename)
            text = extract_text_from_pdf(file_path)
            resumes.append(text)
            resume_names.append(filename)

    # Create a TF-IDF Vectorizer
    vectorizer = TfidfVectorizer(vocabulary=keywords_lower)
    tfidf_matrix = vectorizer.fit_transform(resumes)

    # Calculate cosine similarity
    similarity_matrix = cosine_similarity(tfidf_matrix)

    # Rank resumes based on similarity to keywords
    scores = similarity_matrix.sum(axis=1)
    ranked_resumes = sorted(zip(resume_names, scores), key=lambda x: x[1], reverse=True)

    return ranked_resumes

# Run the ranking
if __name__ == "__main__":
    print(Fore.CYAN + "Select a position to rank resumes:")
    for key, (position, _) in position_map.items():
        print(Fore.YELLOW + f"{key}. {position}")

    # Get user input
    choice = int(input(Fore.CYAN + "Enter the number corresponding to the position: "))
    
    if choice in position_map:
        position, keywords = position_map[choice]
        cv_folder = os.path.join(BASE_FOLDER, position.lower())  # Path to the folder
        print(Fore.GREEN + f"Selected Position: {position}")
        
        ranked_resumes = rank_resumes(cv_folder, keywords)
        
        # Determine the number of resumes to display
        display_count = min(5, len(ranked_resumes))  # Show top 5 or less if fewer resumes
        
        # Output the rankings
        print(Fore.MAGENTA + "Ranked Resumes:")
        for rank, (resume_name, score) in enumerate(ranked_resumes[:display_count], start=1):
            print(Fore.WHITE + f"Rank {rank}: {resume_name} with score {score:.2f}")

        # Check for user's resume rank and score
        user_rank_info = next(((rank, score) for rank, (name, score) in enumerate(ranked_resumes, start=1) if name == USER_RESUME_NAME), None)
        
        if user_rank_info:
            user_rank, user_score = user_rank_info
            print(Fore.GREEN + f"Your resume '{USER_RESUME_NAME}' is ranked: {user_rank} with a score of {user_score:.2f}")
        else:
            print(Fore.RED + f"Your resume '{USER_RESUME_NAME}' was not found in the rankings.")
    else:
        print(Fore.RED + "Invalid selection. Please run the program again and select a valid option.")