"""벤치마크 단위 테스트 — 후처리 적용 + glossary 지원.

벤치 지표는 원시 전사가 아니라 후처리(rules/glossary)를 거친 결과를 측정해야
한다 (vLLM→BLM 같은 오인식 복원 포함).
"""

from __future__ import annotations

from luke_scribe.benchmark.runner import _run_model, _transcribe_clip
from luke_scribe.config import Settings
from luke_scribe.engine.base import TranscriptionOptions

REF_TEXT = "오늘은 vLLM 서버를 Kubernetes 클러스터에 배포합니다"
ENTITIES = [
    {"canonical": "vLLM", "surface": "vLLM", "start_char": 4, "end_char": 8},
    {"canonical": "Kubernetes", "surface": "Kubernetes", "start_char": 13, "end_char": 23},
]


class _FakeOwner:
    """세그먼트 dict를 반환하는 가짜 owner (dict 계약 사용)."""

    def __init__(self, texts: list[str]) -> None:
        self._texts = texts

    def transcribe(self, req):  # noqa: ANN001
        segs = [
            {
                "index": i,
                "start": i * 2.0,
                "end": i * 2.0 + 2.0,
                "text": t,
                "avg_logprob": -0.2,
                "no_speech_prob": 0.01,
            }
            for i, t in enumerate(self._texts)
        ]
        return {
            "segments": iter(segs),
            "device": "cpu",
            "compute_type": "int8",
            "attempted_profiles": [{}],
            "info": {"language": "ko"},
        }


class TestTranscribeClipPostprocess:
    def test_rules_fix_blm_to_vllm(self):
        owner = _FakeOwner(["오늘은 BLM 서버를 Kubernetes 클러스터에 배포합니다"])
        settings = Settings(_env_file=None, post_mode="rules", post_enabled=True)
        clip = {"audio_path": "x.mp3", "duration_sec": 10.0}
        out = _transcribe_clip(owner, TranscriptionOptions(), clip, settings, None)
        assert "vLLM" in out["text"]
        assert "BLM" not in out["text"]

    def test_glossary_applied(self):
        owner = _FakeOwner(["브이엘엘엠 서버"])
        settings = Settings(_env_file=None, post_mode="glossary", post_enabled=True)
        clip = {"audio_path": "x.mp3", "duration_sec": 10.0}
        out = _transcribe_clip(
            owner, TranscriptionOptions(), clip, settings, {"브이엘엘엠": "vLLM"}
        )
        assert "vLLM" in out["text"]

    def test_postprocess_disabled_keeps_raw(self):
        owner = _FakeOwner(["오늘은 BLM 서버"])
        settings = Settings(_env_file=None, post_mode="rules", post_enabled=False)
        clip = {"audio_path": "x.mp3", "duration_sec": 10.0}
        out = _transcribe_clip(owner, TranscriptionOptions(), clip, settings, None)
        assert "BLM" in out["text"]


class TestRunModelPostprocess:
    def _report(self) -> dict:
        return {"run_config": {"hotword_set": []}}

    def _clip(self, ref_path: str) -> dict:
        return {
            "id": "c1",
            "audio_path": "x.mp3",
            "reference_path": ref_path,
            "duration_sec": 10.0,
            "entities": ENTITIES,
        }

    def test_entity_retention_full_with_rules(self, tmp_path):
        ref = tmp_path / "ref.txt"
        ref.write_text(REF_TEXT, encoding="utf-8")
        owner = _FakeOwner(["오늘은 BLM 서버를 Kubernetes 클러스터에 배포합니다"])
        settings = Settings(_env_file=None, post_mode="rules", post_enabled=True)
        agg = _run_model(
            owner,
            [self._clip(str(ref))],
            "large-v3-turbo",
            "cpu",
            "int8",
            1,
            [],
            self._report(),
            settings,
            None,
        )
        assert agg["summary"]["entity_retention"] == 1.0
        assert agg["summary"]["failure_rate"] == 0.0

    def test_glossary_raises_entity_retention(self, tmp_path):
        ref = tmp_path / "ref.txt"
        ref.write_text(REF_TEXT, encoding="utf-8")
        owner = _FakeOwner(["오늘은 BLM 서버를 Kubernetes 클러스터에 배포합니다"])
        settings = Settings(_env_file=None, post_mode="glossary", post_enabled=True)
        agg = _run_model(
            owner,
            [self._clip(str(ref))],
            "large-v3-turbo",
            "cpu",
            "int8",
            1,
            [],
            self._report(),
            settings,
            {"BLM": "vLLM"},
        )
        assert agg["summary"]["entity_retention"] == 1.0

    def test_raw_text_fails_entity_retention_without_postprocess(self, tmp_path):
        # 후처리 없이 raw 전사("BLM")를 측정하면 vLLM 엔티티가 보존되지 않는다
        ref = tmp_path / "ref.txt"
        ref.write_text(REF_TEXT, encoding="utf-8")
        owner = _FakeOwner(["오늘은 BLM 서버를 Kubernetes 클러스터에 배포합니다"])
        settings = Settings(_env_file=None, post_mode="none", post_enabled=False)
        agg = _run_model(
            owner,
            [self._clip(str(ref))],
            "large-v3-turbo",
            "cpu",
            "int8",
            1,
            [],
            self._report(),
            settings,
            None,
        )
        assert agg["summary"]["entity_retention"] < 1.0