test_utils.py

# Tests for the shared utility functions
# Run: python -m pytest test_utils.py -v

def test_preprocess_text_strips_html():
    from utils import preprocess_text
    result = preprocess_text('<b>Hello</b> world')
    assert '<' not in result
    assert '>' not in result

def test_preprocess_text_removes_urls():
    from utils import preprocess_text
    result = preprocess_text('Visit http://example.com for details')
    assert 'http' not in result

def test_preprocess_text_removes_emails():
    from utils import preprocess_text
    result = preprocess_text('Contact user@example.com for info')
    assert '@' not in result

def test_preprocess_text_lowercases():
    from utils import preprocess_text
    result = preprocess_text('HELLO WORLD')
    assert result == result.lower()

def test_preprocess_text_removes_stopwords():
    from utils import preprocess_text
    result = preprocess_text('this is a test of the system')
    assert 'this' not in result.split()
    assert 'the' not in result.split()

def test_preprocess_text_empty_input():
    from utils import preprocess_text
    result = preprocess_text('')
    assert result == ''


import numpy as np

def test_compute_metadata_features_shape():
    from utils import compute_metadata_features
    result = compute_metadata_features(['Hello world!', 'Buy now!!!'])
    assert isinstance(result, np.ndarray)
    assert result.shape == (2, 24)

def test_compute_metadata_features_exclamation_density():
    from utils import compute_metadata_features
    # 'Buy now!!!' has 3 exclamation marks and 1 sentence -> density = 3.0
    result = compute_metadata_features(['Buy now!!!'])
    exclamation_density = result[0][0]
    assert exclamation_density == 3.0

def test_compute_metadata_features_dollar_count():
    from utils import compute_metadata_features
    result = compute_metadata_features(['Win $100 or $200'])
    dollar_count = result[0][1]
    assert dollar_count == 2

def test_compute_metadata_features_spam_phrases():
    from utils import compute_metadata_features
    # 'act now' and 'buy now' are both in the spam_context_phrases list
    result = compute_metadata_features(['Act now! Buy now!'])
    spam_phrase_count = result[0][3]
    assert spam_phrase_count >= 2