"""
utils.py -- Helper functions used across the RAG-lite pipeline.
"""

import re
from datetime import datetime


def validate_inputs(text: str, question: str) -> tuple[bool, str]:
    """Basic input validation. Returns (is_valid, error_message)."""
    if not text or not text.strip():
        return False, "Please provide a paragraph or text to analyze."
    if len(text.strip().split()) < 10:
        return False, "Text is too short. Please provide at least a few sentences."
    if not question or not question.strip():
        return False, "Please enter a question."
    if len(question.strip()) < 3:
        return False, "Question seems too short. Try asking something more specific."
    return True, ""


def format_debug_info(chunks: list[str], scores: list[float]) -> str:
    """Readable debug string showing retrieved chunks and similarity scores."""
    if not chunks:
        return "No chunks retrieved."

    lines = ["Debug Info -- Top Retrieved Chunks\n"]
    for i, (chunk, score) in enumerate(zip(chunks, scores), start=1):
        preview = chunk.strip()[:200] + ("..." if len(chunk) > 200 else "")
        lines.append(f"[Chunk {i}] Similarity Score: {score:.4f}")
        lines.append(preview)
        lines.append("")

    return "\n".join(lines)


def format_context_display(chunks: list[str], metadata: list[dict]) -> str:
    """Show which parts of the text were used to form the answer."""
    if not chunks:
        return ""

    parts = ["Relevant context used:\n"]
    for i, (chunk, meta) in enumerate(zip(chunks, metadata), start=1):
        start   = meta.get("start_word", "?")
        end     = meta.get("end_word", "?")
        preview = chunk.strip()[:300] + ("..." if len(chunk) > 300 else "")
        parts.append(f"[Segment {i} -- words {start} to {end}]\n{preview}\n")

    return "\n".join(parts)


def clean_text(text: str) -> str:
    """Normalize whitespace and collapse blank lines."""
    text = re.sub(r"\n{3,}", "\n\n", text)
    text = re.sub(r"[ \t]+", " ", text)
    return text.strip()


def format_multi_answer_output(qa_pairs: list[dict]) -> str:
    """
    Format multiple Q/A pairs into clean professional output.
    No separator lines. Each pair separated by a blank line.

    Example output:
        Question 1: What is machine learning?
        Machine learning is a subset of artificial intelligence that enables
        systems to learn patterns from data and improve performance over time.

        Question 2: What are its types?
        The types include supervised learning and unsupervised learning.

        Question 3: What are its applications?
        Machine learning is used in recommendation systems, fraud detection,
        healthcare diagnostics, and autonomous vehicles.
    """
    if not qa_pairs:
        return ""

    lines = []
    for i, pair in enumerate(qa_pairs, start=1):
        q = pair.get("question", "").strip()
        a = pair.get("answer", "").strip()
        lines.append(f"Question {i}: {q}")
        lines.append(a)
        if i < len(qa_pairs):
            lines.append("")

    return "\n".join(lines)