rar-autopass/tests/test_embeddings.py

"""
Teste pentru app/embeddings.py -- modul embedding in-proces (L14-S4).

Structura:
  (a) backend MOCK (vectori deterministi) -- index + suggest_nearest
  (b) degradare gratioasa: backend None/broken -> is_available()=False,
      suggest_nearest()=[] fara exceptie
  (c) test real fastembed, skip daca nu e instalat (marker slow)
"""
import math
import pytest

from app import embeddings as emb
from app.embeddings import EmbeddingEngine


# --------------------------------------------------------------------------- #
# Helpers                                                                     #
# --------------------------------------------------------------------------- #

def _vec(text: str, dim: int = 8) -> list:
    """Vector determinist bazat pe hash-ul textului (mock pur, fara retea)."""
    h = abs(hash(text))
    components = [(h >> (i * 5)) & 0x1F for i in range(dim)]
    norm = math.sqrt(sum(c * c for c in components)) or 1.0
    return [c / norm for c in components]


class MockBackend:
    """Backend embedding determinist pentru teste."""

    def embed(self, texts: list) -> list:
        return [_vec(t) for t in texts]


# --------------------------------------------------------------------------- #
# (a) Mock backend -- index + suggest_nearest                                 #
# --------------------------------------------------------------------------- #

def test_index_and_suggest_nearest_mock():
    """Cel mai apropiat vecin al unui text identic == el insusi."""
    corpus = [
        {"denumire": "SCHIMB ULEI", "cod": "OE-3"},
        {"denumire": "REPARATIE MOTOR", "cod": "OE-1"},
        {"denumire": "VERIFICARE DIRECTIE", "cod": "OE-4"},
    ]
    engine = EmbeddingEngine(backend=MockBackend())
    engine.index_corpus(corpus)

    results = engine.suggest_nearest("SCHIMB ULEI", top_k=1)
    assert results, "Trebuie sa returneze cel putin un rezultat"
    assert results[0]["cod"] == "OE-3"
    assert 0.0 <= results[0]["similaritate"] <= 1.0 + 1e-9


def test_suggest_nearest_top_k_respects_limit():
    """suggest_nearest(top_k=2) nu returneaza mai mult de 2 rezultate."""
    corpus = [
        {"denumire": "SCHIMB ULEI MOTOR", "cod": "OE-3"},
        {"denumire": "REVIZIE COMPLETA", "cod": "OE-3"},
        {"denumire": "REPARATIE MOTOR", "cod": "OE-1"},
        {"denumire": "INLOCUIT FRANA", "cod": "OE-2"},
    ]
    engine = EmbeddingEngine(backend=MockBackend())
    engine.index_corpus(corpus)

    results = engine.suggest_nearest("ULEI MOTOR", top_k=2)
    assert len(results) <= 2


def test_suggest_nearest_sorted_descending():
    """Rezultatele sunt sortate descrescator dupa similaritate."""
    corpus = [
        {"denumire": "SCHIMB ULEI", "cod": "OE-3"},
        {"denumire": "REPARATIE MOTOR", "cod": "OE-1"},
        {"denumire": "VERIFICARE FRANURI", "cod": "OE-2"},
    ]
    engine = EmbeddingEngine(backend=MockBackend())
    engine.index_corpus(corpus)

    results = engine.suggest_nearest("SCHIMB ULEI", top_k=3)
    scores = [r["similaritate"] for r in results]
    assert scores == sorted(scores, reverse=True)


def test_suggest_nearest_returns_dict_with_required_keys():
    """Fiecare rezultat contine 'cod' si 'similaritate'."""
    corpus = [{"denumire": "SCHIMB ULEI", "cod": "OE-3"}]
    engine = EmbeddingEngine(backend=MockBackend())
    engine.index_corpus(corpus)

    results = engine.suggest_nearest("SCHIMB ULEI", top_k=1)
    assert results
    assert "cod" in results[0]
    assert "similaritate" in results[0]


def test_index_empty_corpus():
    """suggest_nearest pe corpus gol returneaza []."""
    engine = EmbeddingEngine(backend=MockBackend())
    engine.index_corpus([])
    assert engine.suggest_nearest("CEVA", top_k=3) == []


def test_suggest_nearest_before_index():
    """suggest_nearest fara index_corpus returneaza []."""
    engine = EmbeddingEngine(backend=MockBackend())
    assert engine.suggest_nearest("CEVA", top_k=3) == []


def test_engine_is_available_with_backend():
    """is_available() = True cand backend-ul e furnizat."""
    engine = EmbeddingEngine(backend=MockBackend())
    assert engine.is_available() is True


# --------------------------------------------------------------------------- #
# (b) Degradare gratioasa -- backend None / arunca                           #
# --------------------------------------------------------------------------- #

def test_is_available_false_when_backend_none():
    """is_available() = False cand backend = None."""
    engine = EmbeddingEngine(backend=None)
    assert engine.is_available() is False


def test_suggest_nearest_returns_empty_when_backend_none():
    """suggest_nearest = [] fara exceptie cand backend = None."""
    engine = EmbeddingEngine(backend=None)
    result = engine.suggest_nearest("CEVA", top_k=3)
    assert result == []


def test_index_corpus_no_exception_when_backend_none():
    """index_corpus nu arunca exceptie cand backend = None."""
    engine = EmbeddingEngine(backend=None)
    engine.index_corpus([{"denumire": "CEVA", "cod": "OE-1"}])  # nu arunca


def test_suggest_nearest_no_exception_on_backend_error():
    """suggest_nearest prinde exceptia din backend si returneaza []."""

    class BrokenBackend:
        def embed(self, texts):
            raise RuntimeError("backend broke")

    corpus = [{"denumire": "SCHIMB ULEI", "cod": "OE-3"}]
    engine = EmbeddingEngine(backend=BrokenBackend())
    engine.index_corpus(corpus)  # index poate esua silentios

    # suggest_nearest nu trebuie sa arunce exceptie
    result = engine.suggest_nearest("SCHIMB ULEI", top_k=1)
    assert result == []


def test_index_corpus_no_exception_on_backend_error():
    """index_corpus nu arunca exceptie cand backend-ul arunca la embed."""

    class BrokenBackend:
        def embed(self, texts):
            raise ValueError("embed error")

    engine = EmbeddingEngine(backend=BrokenBackend())
    engine.index_corpus([{"denumire": "CEVA", "cod": "OE-1"}])
    # corpus ramane gol, suggest_nearest returneaza []
    assert engine.suggest_nearest("CEVA") == []


# --------------------------------------------------------------------------- #
# API la nivel de modul (singleton global)                                   #
# --------------------------------------------------------------------------- #

def test_module_level_is_available_no_exception():
    """Apelul global is_available() nu arunca exceptie."""
    result = emb.is_available()
    assert isinstance(result, bool)


def test_module_level_suggest_nearest_no_exception():
    """Apelul global suggest_nearest() nu arunca exceptie."""
    result = emb.suggest_nearest("SCHIMB ULEI MOTOR", top_k=3)
    assert isinstance(result, list)


def test_module_level_index_corpus_no_exception():
    """Apelul global index_corpus() nu arunca exceptie."""
    corpus = [{"denumire": "REPARATIE", "cod": "OE-1"}]
    emb.index_corpus(corpus)  # nu trebuie sa arunce


# --------------------------------------------------------------------------- #
# (c) Test real fastembed -- skip daca modelul nu e descarcat                #
# --------------------------------------------------------------------------- #

try:
    import fastembed as _fe
    _FASTEMBED_AVAILABLE = True
except ImportError:
    _FASTEMBED_AVAILABLE = False


@pytest.mark.skipif(not _FASTEMBED_AVAILABLE, reason="fastembed nu e instalat")
def test_fastembed_backend_is_available_type():
    """is_available() returneaza bool (indiferent daca modelul e descarcat sau nu)."""
    result = emb.is_available()
    assert isinstance(result, bool)


@pytest.mark.slow
@pytest.mark.skipif(not _FASTEMBED_AVAILABLE, reason="fastembed nu e instalat")
def test_fastembed_real_embedding_similarity():
    """Test real end-to-end: denumiri similare au similaritate mai mare decat cele diferite.

    Necesita download model la prima rulare (~220MB). Skip cu: pytest -m 'not slow'.
    """
    from app.embeddings import EmbeddingEngine, FastEmbedBackend

    backend = FastEmbedBackend()
    engine = EmbeddingEngine(backend=backend)

    corpus = [
        {"denumire": "schimb ulei motor", "cod": "OE-3"},
        {"denumire": "reparatie motor cutie viteze", "cod": "OE-1"},
        {"denumire": "verificare directie volan", "cod": "OE-4"},
    ]
    engine.index_corpus(corpus)

    results = engine.suggest_nearest("schimb ulei", top_k=3)
    assert results, "Trebuie sa returneze cel putin un rezultat"
    # 'schimb ulei' trebuie sa fie mai aproape de 'schimb ulei motor' (OE-3)
    assert results[0]["cod"] == "OE-3", (
        f"Asteptat OE-3 ca primul rezultat, primit: {results}"
    )