tests/test_scorer.py

import pytest
import numpy as np
from app.scorer import cosine_similarity, DimensionalityMismatchError, ZeroVectorError, EmptyInputError


@pytest.fixture
def valid_input():
    query_vector = np.array([[1, 0]])
    corpus_vectors = np.array([[1, 0], [0, 1], [1, 1]])
    return query_vector, corpus_vectors


@pytest.fixture
def zero_query_vector():
    query_vector = np.array([[0, 0]])
    corpus_vectors = np.array([[1, 0], [0, 1]])
    return query_vector, corpus_vectors


@pytest.fixture
def corpus_with_zero_vector():
    query_vector = np.array([[1, 1]])
    corpus_vectors = np.array([[1, 0], [0, 1], [0, 0]])
    return query_vector, corpus_vectors


@pytest.fixture
def dimensionality_mismatch():
    query_vector = np.array([[1, 0]])
    corpus_vectors = np.array([[1, 0, 0], [0, 1, 0]])
    return query_vector, corpus_vectors


@pytest.fixture
def empty_input():
    query_vector = np.array([[]])
    corpus_vectors = np.array([[]])
    return query_vector, corpus_vectors


@pytest.mark.unit
def test_cosine_similarity_valid_input(valid_input):
    query_vector, corpus_vectors = valid_input
    similarities = cosine_similarity(query_vector, corpus_vectors)
    assert isinstance(similarities, np.ndarray)
    assert similarities.shape == (3,)
    assert similarities[0] == pytest.approx(1.0)  # Same direction
    assert similarities[1] == pytest.approx(0.0)  # Orthogonal
    assert similarities[2] == pytest.approx(1 / np.sqrt(2))  # Diagonal similarity


@pytest.mark.unit
def test_cosine_similarity_zero_query_vector(zero_query_vector):
    query_vector, corpus_vectors = zero_query_vector
    with pytest.raises(ZeroVectorError):
        cosine_similarity(query_vector, corpus_vectors)


@pytest.mark.unit
def test_cosine_similarity_corpus_with_zero_vector(corpus_with_zero_vector):
    query_vector, corpus_vectors = corpus_with_zero_vector
    with pytest.raises(ZeroVectorError):
        cosine_similarity(query_vector, corpus_vectors)


@pytest.mark.unit
def test_cosine_similarity_dimensionality_mismatch(dimensionality_mismatch):
    query_vector, corpus_vectors = dimensionality_mismatch
    with pytest.raises(DimensionalityMismatchError):
        cosine_similarity(query_vector, corpus_vectors)


@pytest.mark.unit
def test_cosine_similarity_empty_inputs(empty_input):
    query_vector, corpus_vectors = empty_input
    with pytest.raises(EmptyInputError):
        cosine_similarity(query_vector, corpus_vectors)


@pytest.mark.integration
def test_cosine_similarity_output_range(valid_input):
    query_vector, corpus_vectors = valid_input
    similarities = cosine_similarity(query_vector, corpus_vectors)
    assert np.all(similarities >= -1)
    assert np.all(similarities <= 1)