import pdfplumber
import spacy

# Load NLP Model
nlp = spacy.load("en_core_web_sm")

# Predefined ATS-friendly keywords
REQUIRED_SKILLS = {"Python", "Machine Learning", "NLP", "Deep Learning", "AI", "Data Science", "Cloud", "Hugging Face"}

def extract_text_from_pdf(pdf_path):
    """Extract text from a resume PDF"""
    text = ""
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text += page.extract_text() + "\n"
    return text.strip()

def analyze_resume(text):
    """Analyze the resume text and provide ATS recommendations"""
    doc = nlp(text)

    # Extract skills
    words = set([token.text for token in doc if token.is_alpha])
    matched_skills = REQUIRED_SKILLS.intersection(words)
    missing_skills = REQUIRED_SKILLS - matched_skills

    # Calculate ATS Score
    ats_score = (len(matched_skills) / len(REQUIRED_SKILLS)) * 100

    return {
        "matched_skills": list(matched_skills),
        "missing_skills": list(missing_skills),
        "ats_score": round(ats_score, 2)
    }