"""
تقسیمِ متنِ درس به تکه‌های مستقل + خلاصه‌سازیِ آموزشیِ هر تکه.

برداشتِ پاک‌سازی‌شده از subjects/services/chunker.py مخزنِ Rag_backend:
- به‌جای HttpError نینجا، از استثناهای معمولی استفاده می‌کنیم (لایه‌ی view
  در DRF تبدیلش می‌کنه).
- کلاینت lazy است.
"""
import json

from django.conf import settings

from . import clients


class ChunkingError(RuntimeError):
    pass


def split_text_into_chunks(text: str, chunk_size: int = 400, overlap: int = 100) -> list[str]:
    if not text:
        return []
    chunks: list[str] = []
    start = 0
    text_length = len(text)
    step = max(chunk_size - overlap, 1)
    while start < text_length:
        end = min(start + chunk_size, text_length)
        chunks.append(text[start:end])
        start += step
    return chunks


def _strip_code_fence(raw: str) -> str:
    raw = raw.strip()
    if raw.startswith('```json'):
        raw = raw[len('```json'):]
    elif raw.startswith('```'):
        raw = raw[len('```'):]
    if raw.endswith('```'):
        raw = raw[:-3]
    return raw.strip()


def summarize_chunk(chunk_text: str) -> str:
    """خلاصه‌ی مستقل و آموزشیِ یک تکه به فارسی."""
    prompt = f"""
    You are an expert Persian educational summarizer.
    Summarize the following text clearly and independently.

    - The summary must be self-contained.
    - Capture all key educational points.
    - Write in natural Persian (Farsi).

    Text:
    {chunk_text}

    Return JSON only:
    {{"summary": "خلاصه کامل این بخش در فارسی"}}
    """
    client = clients.get_openai_client()
    response = client.chat.completions.create(
        model=settings.OPENAI_CHAT_MODEL,
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant that always outputs valid JSON.'},
            {'role': 'user', 'content': prompt},
        ],
        max_tokens=400,
        temperature=0.4,
        top_p=0.9,
    )
    raw = _strip_code_fence(response.choices[0].message.content or '')
    try:
        data = json.loads(raw)
    except json.JSONDecodeError as exc:
        raise ChunkingError(f'خروجیِ خلاصه‌سازی JSON معتبر نبود: {raw[:300]}') from exc
    summary = data.get('summary')
    if not summary:
        raise ChunkingError(f'کلیدِ summary در خروجی نبود: {raw[:300]}')
    return summary


def chunk_and_summarize(text: str, chunk_size: int = 400, overlap: int = 100) -> list[dict]:
    """[{order, original_text, summary}, ...]"""
    result = []
    for index, original in enumerate(split_text_into_chunks(text, chunk_size, overlap), start=1):
        result.append({
            'order': index,
            'original_text': original,
            'summary': summarize_chunk(original),
        })
    return result