utils/reporting.py

# utils/reporting.py
import re
import fitz  # PyMuPDF
from io import BytesIO
from config import supabase, embedding_model, client, query
from .screening import evaluate_resumes

def generate_pdf_report(shortlisted_candidates, questions=None):
    """
    Creates a PDF report summarizing top candidates and interview questions.
    """
    pdf = BytesIO()
    doc = fitz.open()

    for candidate in shortlisted_candidates:
        page = doc.new_page()
        info = (
            f"Candidate: {candidate['name']}\n"
            f"Email: {candidate['email']}\n"
            f"Score: {candidate['score']}\n\n"
            f"Summary:\n{candidate.get('summary', 'No summary available')}"
        )
        page.insert_textbox(fitz.Rect(50, 50, 550, 750), info, fontsize=11, fontname="helv", align=0)

    if questions:
        q_page = doc.new_page()
        q_text = "Suggested Interview Questions:\n\n" + "\n".join(questions)
        q_page.insert_textbox(fitz.Rect(50, 50, 550, 750), q_text, fontsize=11, fontname="helv", align=0)

    doc.save(pdf)
    pdf.seek(0)
    return pdf


def generate_interview_questions_from_summaries(candidates):
    if not isinstance(candidates, list):
        raise TypeError("Expected a list of candidate dictionaries.")

    summaries = " ".join(c.get("summary", "") for c in candidates)

    prompt = (
        "Based on the following summary of a top candidate for a job role, "
        "generate 5 thoughtful, general interview questions that would help a recruiter assess their fit:\n\n"
        f"{summaries}"
    )

    try:
        response = client.chat.completions.create(
            model="tgi",
            messages=[{"role": "user", "content": prompt}],
            temperature=0.7,
            max_tokens=500,
)

        result = response.choices[0].message.content

        # Clean and normalize questions
        raw_questions = result.split("\n")
        questions = []

        for q in raw_questions:
            q = q.strip()

            # Skip empty lines and markdown headers
            if not q or re.match(r"^#+\s*", q):
                continue

            # Remove leading bullets like "1.", "1)", "- 1.", etc.
            q = re.sub(r"^(?:[-*]?\s*)?(?:Q?\d+[\.\)\-]?\s*)+", "", q)

            # Remove markdown bold/italics (**, *, etc.)
            q = re.sub(r"[*_]+", "", q)
            
            # Remove duplicate trailing punctuation
            q = q.strip(" .")

            questions.append(q.strip())
            
        return [f"Q{i+1}. {q}" for i, q in enumerate(questions[:5])] or ["⚠️ No questions generated."]
    
    except Exception as e:
        print(f"❌ Error generating interview questions: {e}")
        return ["⚠️ Error generating questions."]