import os
import pickle
from tkinter import Tk, filedialog
import docx2txt
import PyPDF2
from sklearn.feature_extraction.text import TfidfVectorizer

# Load trained vectorizer and model
VECTORIZER_PATH = r'F:\New folder (2)\resume-analyzer\models\vectorizer.pkl'
MODEL_PATH = r'F:\New folder (2)\resume-analyzer\models\model.pkl'

vectorizer = pickle.load(open(VECTORIZER_PATH, 'rb'))
model = pickle.load(open(MODEL_PATH, 'rb'))

def extract_text_from_pdf(file_path):
    try:
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            return " ".join([page.extract_text() or "" for page in pdf_reader.pages])
    except Exception as e:
        print(f"Error reading PDF: {e}")
        return ""

def extract_text_from_docx(file_path):
    try:
        return docx2txt.process(file_path)
    except Exception as e:
        print(f"Error reading DOCX: {e}")
        return ""

def predict_resume_category():
    # File dialog
    root = Tk()
    root.withdraw()  # Hide the main window
    file_path = filedialog.askopenfilename(title="Select Resume File", filetypes=[("Documents", "*.pdf *.docx")])
    root.destroy()

    if not file_path:
        print("❌ No file selected.")
        return

    file_extension = os.path.splitext(file_path)[1].lower()
    text = ""

    if file_extension == ".pdf":
        text = extract_text_from_pdf(file_path)
    elif file_extension == ".docx":
        text = extract_text_from_docx(file_path)
    else:
        print("❌ Unsupported file type. Please upload a PDF or DOCX.")
        return

    if not text.strip():
        print("❌ No readable text found in the resume.")
        return

    # Predict category
    input_vector = vectorizer.transform([text])
    prediction = model.predict(input_vector)

    print(f"✅ Predicted Resume Category: {prediction[0]}")

if __name__ == "__main__":
    predict_resume_category()