def test_get_paper_name():
    assert get_paper_name(15) == 'papers/federalist_15.txt'
    assert get_paper_name(3) == 'papers/federalist_3.txt'
    print('test_get_paper_name() successful')

def test_get_paper_text():
    text = get_paper_text(15)
    assert len(text) == 18513
    assert 'It has its origin in the love of power.' in text
    print('test_get_paper_text() successful')

def test_average_word_length():
    eps = 1e-7
    data = [(['a', 'ab', 'abc'], 2.0),
            (['a', 'b', 'c'], 1.0),
            (['a', 'ab', 'abc', 'abcd'], 2.5),
            (['a'], 1.0),
            ]
    for words, expected_avg in data:
        calculated_avg = average_word_length(words)
        msg = (str(words) + ' expected avg ' + str(expected_avg) +
               ' but calculated avg ' + str(calculated_avg))
        assert abs(calculated_avg - expected_avg) < eps, msg
    print('test_average_word_length() successful')


def test_paper_avg_word_len():
    eps = 1e-7
    expected_vals = [4.874692874692875,
                     5.029011249259917,
                     5.031313818924438,
                     4.930639324487334,
                     5.125730994152047]
    for n in range(1, 6):
        calculated_avg = paper_avg_word_len(n)
        expected_avg = expected_vals[n-1]
        msg = ('Paper' + str(n) + ' expected avg ' + str(expected_avg) +
               ' but calculated avg ' + str(calculated_avg))
        assert abs(calculated_avg - expected_avg) < eps, msg
    print('test_paper_avg_word_len() successful')


def test_collection_avg_word_len():
    eps = 1e-7
    expected_vals = [4.874692874692875,
                     4.951852061976396,
                     4.97833931429241,
                     4.966414316841141, ]
    for max_paper_num in range(1, 5):
        paper_nums = list(range(1, max_paper_num + 1))
        calculated_avg = collection_avg_word_len(paper_nums)
        expected_avg = expected_vals[max_paper_num - 1]
        msg = ('Papers 1-' + str(max_paper_num) + ' expected avg ' + str(expected_avg) +
               ' but calculated avg ' + str(calculated_avg))
        assert abs(calculated_avg - expected_avg) < eps, msg
    print('test_collection_avg_word_len() successful')


def test_guess_paper_by_word_len():
    expected_vals = ['Hamilton', 'Madison', 'Madison', 'Hamilton', 'Madison', 'Madison',
                     'Madison', 'Madison',
                     'Madison', 'Jay', 'Jay', 'Jay', 'Jay', 'Hamilton',
                     'Hamilton', 'Hamilton', 'Madison', 'Madison', 'Madison']
    for n in range(1, 20):
        calculated_author = guess_paper_by_word_len(n)
        expected_author = expected_vals[n - 1]
        msg = ('Paper' + str(n) + ' expected author ' + str(expected_author) +
               ' but calculated author ' + str(calculated_author))
        assert calculated_author == expected_author, msg
    print('test_guess_paper_by_word_len() successful')


def test_get_word_counts():
    data = [(['a', 'a', 'a'], {'a': 3}),
            (['a', 'b', 'a', 'b', 'a'], {'a': 3, 'b': 2}),
            (['a', 'b', 'a', 'cccc', 'b', 'a'], {'a': 3, 'b': 2, 'cccc': 1}),
            ]

    for words, expected_counts in data:
        calculated_counts = get_word_counts(words)
        msg = ('Word list' + str(words) + ' expected counts ' + str(expected_counts) +
               ' but calculated ' + str(calculated_counts))
        assert calculated_counts == expected_counts, msg
    print('test_get_word_counts() successful')

def test_type_token_ratio():
    eps = 1e-7
    data = [(['the', 'orange', 'cat', 'sat', 'on', 'the', 'orange', 'mat'], 0.75),
            (['a', 'a', 'a'], 1 / 3),
            (['a', 'b', 'c'], 1.0),
            (['a', 'ab', 'ab', 'abc', 'abcd'], 0.8),
            (['a'], 1.0),
            ]
    for words, expected in data:
        calculated = type_token_ratio(words)
        msg = (str(words) + ' expected type_token_ratio ' + str(expected) +
               ' but calculated type_token_ratio ' + str(calculated))
        assert abs(calculated - expected) < eps, msg
    print('test_type_token_ratio() successful')