import google.generativeai as genai
import streamlit as st
import fitz
import spacy
from docx import Document
import dateparser
from datetime import datetime
from giner import GiNER

# Load SpaCy model
nlp = spacy.load('en_core_web_sm')

# Load GLiNER model
giner = GiNER("roberta-large")

def extract_text_from_pdf(file):
    pdf = fitz.open(stream=file.read(), filetype="pdf")
    text = ""
    for page in pdf:
        text += page.get_text()
    return text

def extract_text_from_doc(file):
    doc = Document(file)
    return " ".join([paragraph.text for paragraph in doc.paragraphs])

def authenticate_gemini(api_key):
    try:
        genai.configure(api_key=api_key)
        model = genai.GenerativeModel('gemini-pro')
        return model
    except Exception as e:
        st.error(f"Authentication failed: {e}")
        return None

def generate_summary(text, model):
    prompt = f"Summarize the following resume:\n\n{text}\n\nProvide a brief overview of the candidate's qualifications, experience, and key skills."
    response = model.generate_content(prompt)
    return response.text

def extract_info(text):
    doc = nlp(text)
    giner_results = giner.annotate(text)

    # Extract companies
    companies = set([ent.text for ent in doc.ents if ent.label_ == "ORG"])
    companies.update([entity['text'] for entity in giner_results if entity['type'] == "ORG"])

    # Extract experience
    experience = max([datetime.now().year - date.year for ent in doc.ents if ent.label_ == "DATE" and (date := dateparser.parse(ent.text)) and date.year <= datetime.now().year] or [0])

    # Extract education
    education = set([ent.text for ent in doc.ents if ent.label_ == "ORG" and any(keyword in ent.text.lower() for keyword in ["university", "college", "institute", "school"])])
    education.update([entity['text'] for entity in giner_results if entity['type'] == "ORG" and any(keyword in entity['text'].lower() for keyword in ["university", "college", "institute", "school"])])

    # Extract contact information
    email = next((ent.text for ent in doc.ents if ent.label_ == "EMAIL"), "Not found")
    phone = next((ent.text for ent in doc.ents if ent.label_ == "PHONE_NUMBER"), "Not found")

    # Use GLiNER for additional entity extraction
    for entity in giner_results:
        if entity['type'] == "PER" and email == "Not found":
            email = entity['text']
        elif entity['type'] == "PHONE" and phone == "Not found":
            phone = entity['text']

    return list(companies), experience, list(education), email, phone

def main():
    st.title("Enhanced Resume Analyzer")

    api_key = st.secrets["GEMINI_API_KEY"]  # Use Streamlit secrets
    uploaded_file = st.file_uploader("Choose a PDF or DOCX file", type=["pdf", "docx"])

    if uploaded_file is not None:
        try:
            model = authenticate_gemini(api_key)
            if model is None:
                return

            if uploaded_file.type == "application/pdf":
                resume_text = extract_text_from_pdf(uploaded_file)
            elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
                resume_text = extract_text_from_doc(uploaded_file)
            else:
                st.error("Unsupported file format.")
                return

            companies, experience, education, email, phone = extract_info(resume_text)

            st.subheader("Extracted Information")
            st.write(f"*Years of Experience:* {experience}")
            st.write("*Companies:*", ", ".join(companies))
            st.write("*Education:*", ", ".join(education))
            st.write(f"*Email:* {email}")
            st.write(f"*Phone:* {phone}")

            summary = generate_summary(resume_text, model)
            st.subheader("Resume Summary")
            st.write(summary)

        except Exception as e:
            st.error(f"Error during processing: {str(e)}")
            st.exception(e)  # This will print the full traceback

if __name__ == "__main__":
    main()