from __future__ import annotations

import sys
import types

from reranker.backends import get_rerank_backend
from reranker.backends.qwen3_gguf import Qwen3GGUFRerankerBackend


class _FakeLlama:
    def __init__(self, model_path: str | None = None, **kwargs):
        self.model_path = model_path
        self.kwargs = kwargs
        self.eval_logits = []
        self._tokens = []
        self.eval_call_count = 0

    @classmethod
    def from_pretrained(cls, repo_id: str, filename: str, local_dir=None, cache_dir=None, **kwargs):
        inst = cls(model_path=f"{repo_id}/{filename}", **kwargs)
        inst.repo_id = repo_id
        inst.filename = filename
        inst.local_dir = local_dir
        inst.cache_dir = cache_dir
        return inst

    def tokenize(self, text: bytes, add_bos: bool = False, special: bool = False):
        raw = text.decode("utf-8")
        if raw == "yes":
            return [1]
        if raw == "no":
            return [2]
        return [10 + (ord(ch) % 17) for ch in raw]

    def reset(self):
        self._tokens = []
        return None

    def eval(self, prompt_tokens):
        self.eval_call_count += 1
        self._tokens.extend(prompt_tokens)
        pos = float(sum(self._tokens) % 11) + 3.0
        neg = 1.0
        logits = [0.0] * 64
        logits[1] = pos
        logits[2] = neg
        self.eval_logits = [logits]

    def save_state(self):
        return list(self._tokens)

    def load_state(self, state):
        self._tokens = list(state)


def _install_fake_llama_cpp(monkeypatch):
    fake_module = types.SimpleNamespace(Llama=_FakeLlama)
    monkeypatch.setitem(sys.modules, "llama_cpp", fake_module)


def test_qwen3_gguf_backend_factory_loads(monkeypatch):
    _install_fake_llama_cpp(monkeypatch)
    backend = get_rerank_backend(
        "qwen3_gguf",
        {
            "repo_id": "DevQuasar/Qwen.Qwen3-Reranker-4B-GGUF",
            "filename": "*Q8_0.gguf",
            "enable_warmup": False,
        },
    )
    assert isinstance(backend, Qwen3GGUFRerankerBackend)
    assert backend._backend_name == "qwen3_gguf"


def test_qwen3_gguf_06b_backend_factory_loads(monkeypatch):
    _install_fake_llama_cpp(monkeypatch)
    backend = get_rerank_backend(
        "qwen3_gguf_06b",
        {
            "enable_warmup": False,
        },
    )
    assert isinstance(backend, Qwen3GGUFRerankerBackend)
    assert backend._backend_name == "qwen3_gguf_06b"
    assert backend._repo_id == "ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF"
    assert backend._filename == "qwen3-reranker-0.6b-q8_0.gguf"


def test_qwen3_gguf_backend_score_with_meta_dedup_and_restore(monkeypatch):
    _install_fake_llama_cpp(monkeypatch)
    backend = Qwen3GGUFRerankerBackend(
        {
            "repo_id": "DevQuasar/Qwen.Qwen3-Reranker-4B-GGUF",
            "filename": "*Q8_0.gguf",
            "enable_warmup": False,
            "infer_batch_size": 2,
            "sort_by_doc_length": True,
            "reuse_query_state": True,
        }
    )

    scores, meta = backend.score_with_meta(
        query="wireless mouse",
        docs=["doc-a", "doc-b", "doc-a", "", "   ", None],
        normalize=True,
    )

    assert len(scores) == 6
    assert scores[0] == scores[2]
    assert scores[0] > 0.5
    assert scores[1] > 0.5
    assert scores[3:] == [0.0, 0.0, 0.0]
    assert meta["input_docs"] == 6
    assert meta["usable_docs"] == 3
    assert meta["unique_docs"] == 2
    assert meta["backend"] == "qwen3_gguf"
    assert meta["inference_batches"] == 1
    assert meta["reuse_query_state"] is True
    assert backend._llm.eval_call_count == 3