import gradio as gr
from huggingface_hub import InferenceClient
import PyPDF2
import io
from docx import Document
import os
import pymupdf  # Corrected import for PyMuPDF
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.lib import colors

client = InferenceClient(
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    token=os.getenv("HF_TOKEN"))

def extract_text_from_pdf(pdf_file):
    try:
        pdf_document = pymupdf.open(pdf_file)
        text = "".join(page.get_text() for page in pdf_document)
        return text.strip() or "No text could be extracted from the PDF."
    except Exception as e:
        return f"Error reading PDF: {e}"

def extract_text_from_docx(docx_file):
    try:
        doc = Document(docx_file)
        text = "\n".join(para.text for para in doc.paragraphs)
        return text.strip() or "No text could be extracted from the DOCX file."
    except Exception as e:
        return f"Error reading DOCX: {e}"

def parse_cv(file, job_description):
    if file is None:
        return "Please upload a CV file.", ""
    try:
        file_path = file.name
        file_ext = os.path.splitext(file_path)[1].lower()
        extracted_text = extract_text_from_pdf(file_path) if file_ext == ".pdf" else extract_text_from_docx(file_path)
    except Exception as e:
        return f"Error reading file: {e}", ""
    if extracted_text.startswith("Error"):
        return extracted_text, "Error during text extraction."
    prompt = f"Analyze this CV for job relevance.\nJob Description:\n{job_description}\n\nCV:\n{extracted_text}\n"
    try:
        analysis = client.text_generation(prompt, max_new_tokens=512)
        return extracted_text, f"**Analysis Report:**\n{analysis}"
    except Exception as e:
        return extracted_text, f"Analysis Error: {e}"

def create_pdf_report(report_text):
    pdf_buffer = io.BytesIO()
    doc = SimpleDocTemplate(pdf_buffer, pagesize=letter)
    styles = getSampleStyleSheet()
    Story = [Paragraph("<b>Analysis Report</b>", styles['Title']), Spacer(1, 12)]
    Story.append(Paragraph(report_text.replace("\n", "<br/>"), styles['BodyText']))
    doc.build(Story)
    pdf_buffer.seek(0)
    return pdf_buffer.getvalue(), "analysis_report.pdf"

def process_resume(resume_file, job_title):
    if resume_file is None:
        return "Please upload a resume file."
    try:
        file_path = resume_file.name
        file_ext = os.path.splitext(file_path)[1].lower()
        resume_text = extract_text_from_pdf(file_path) if file_ext == ".pdf" else extract_text_from_docx(file_path)
        if resume_text.startswith("Error"):
            return resume_text
        prompt = f"Optimize this resume for {job_title}:\n{resume_text}\n"
        optimized_resume = client.text_generation(prompt, max_new_tokens=1024)
        return optimized_resume.replace("\n", "  \n")  # Ensure Markdown formatting
    except Exception as e:
        return f"Error processing resume: {e}"

demo = gr.Blocks()
with demo:
    gr.Markdown("## AI-powered CV Analyzer and Optimizer")
    
    with gr.Tab("CV Analyzer"):
        file_input = gr.File(label="Upload CV", file_types=[".pdf", ".docx"])
        job_desc_input = gr.Textbox(label="Job Description", lines=5)
        extracted_text = gr.Textbox(label="Extracted CV Content", lines=10, interactive=False)
        analysis_output = gr.Markdown(label="Analysis Report")
        download_pdf_button = gr.Button("Download Analysis as PDF", visible=False)
        pdf_file = gr.File(label="Download PDF", interactive=False)
        analyze_button = gr.Button("Analyze CV")
        analyze_button.click(parse_cv, [file_input, job_desc_input], [extracted_text, analysis_output])
        download_pdf_button.click(create_pdf_report, [analysis_output], [pdf_file])
    
    with gr.Tab("CV Optimizer"):
        resume_file = gr.File(label="Upload Resume (PDF or Word)", file_types=[".pdf", ".docx"])
        job_title_input = gr.Textbox(label="Job Title")
        optimized_resume_output = gr.Markdown(label="Optimized Resume")
        optimize_button = gr.Button("Optimize Resume")
        optimize_button.click(process_resume, [resume_file, job_title_input], [optimized_resume_output])

if __name__ == "__main__":
    demo.queue().launch()