"""postprocess.rules / postprocess.llm (urllib monkeypatch)."""
from __future__ import annotations

import json

import pytest

from luke_scribe.postprocess import llm, rules


def test_rules_normalize():
    assert rules.normalize("구글 Embedding Gemma 소개") == "구글 EmbeddingGemma 소개"
    assert rules.normalize("그대로") == "그대로"


def test_llm_not_configured():
    with pytest.raises(llm.LLMNotConfigured):
        llm.correct("x", base_url=None, api_key=None)


class _FakeResp:
    def __init__(self, payload: dict) -> None:
        self._p = payload

    def read(self) -> bytes:
        return json.dumps(self._p).encode()

    def __enter__(self):
        return self

    def __exit__(self, *_a):
        return False


def test_llm_correct_monkeypatched(monkeypatch):
    def fake_urlopen(_req, timeout=90):  # noqa: ARG001
        return _FakeResp({"choices": [{"message": {"content": "EmbeddingGemma 복원됨"}}]})

    monkeypatch.setattr(llm.urllib.request, "urlopen", fake_urlopen)
    out = llm.correct("인베딩 점마", base_url="http://x/v1", api_key="k", model="m")
    assert out == "EmbeddingGemma 복원됨"


def test_llm_chunking_and_glossary(monkeypatch):
    """긴 입력 → 청크 분할 + 러닝 글로서리(작은 컨텍스트 창 대응)."""
    calls: list[list[dict]] = []

    def fake_request(messages, **_kw):
        calls.append(messages)
        return messages[1]["content"]  # 청크 그대로 echo

    monkeypatch.setattr(llm, "_request", fake_request)
    long_text = ". ".join(f"문장{i} EmbeddingGemma 설명" for i in range(400))
    out = llm.correct(long_text, base_url="http://x/v1", api_key="k", max_chars=200)

    assert len(calls) > 1  # 분할됨
    assert "EmbeddingGemma" in out  # 재조립됨
    # 2번째 청크부터 이전에 확정된 영문 표기가 system에 주입됨
    assert any("확정된 영문 표기" in m[0]["content"] for m in calls[1:])