EnglishPal/test_vocabulary.py

# Run this test script on the command line:
#   pytest test_vocabulary.py
#
# Last modified by Mr Lan Hui on 2025-05-08

from difficulty import (
    user_difficulty_level,
    text_difficulty_level,
    get_difficulty_level_for_user,
    load_record
)

# 词库加载（只加载一次）
d_word_test = load_record("../../../updated_source_code/English Pal/app/oxford_words.txt")
d_difficulty_default = get_difficulty_level_for_user({}, d_word_test)
print(d_difficulty_default)
# ----------------------------- 文章难度测试 -----------------------------

def test_article_level_empty_content():
    level = text_difficulty_level('', d_difficulty_default)
    assert level == 0

def test_article_level_punctuation_only():
    level = text_difficulty_level(',', d_difficulty_default)
    assert level == 0

def test_article_level_digit_only():
    level = text_difficulty_level('1', d_difficulty_default)
    assert level == 0

def test_article_level_single_word():
    level = text_difficulty_level('source', d_difficulty_default)
    assert 2 <= level <= 4

def test_article_level_subset_vs_superset():
    level1 = text_difficulty_level('source', d_difficulty_default)
    level2 = text_difficulty_level('open source', d_difficulty_default)
    print(f"Word: 'source', Difficulty: {d_difficulty_default.get('source', 'Unknown')}")
    assert level1 <= level2

def test_article_level_multiple_words():
    content = 'Producing Open Source Software - How to Run a Successful Free Software Project'
    level = text_difficulty_level(content, d_difficulty_default)
    assert 3 <= level <= 5

def test_article_level_short_paragraph():
    content = ("At parties, people no longer give me a blank stare when I tell them I work in open source software. "
               "‘Oh, yes — like Linux?’ they say. I nod eagerly in agreement. ‘Yes, exactly! That’s what I do.’ "
               "It’s nice not to be completely fringe anymore...")
    level = text_difficulty_level(content, d_difficulty_default)
    assert 4 <= level <= 6

def test_article_level_medium_paragraph():
    content = ("In considering the Origin of Species  it is quite conceivable that a naturalist  reflecting on the mutual affinities of organic being ")  # truncated for brevity
    level = text_difficulty_level(content, d_difficulty_default)
    for word in content.split():
        print(f"Word: {word} , Difficulty: {d_difficulty_default.get(word.lower(), 'Unknown')}")

    assert 5 <= level <= 7

def test_article_level_long_paragraph():
    content = ("These several facts accord well with my theory. I believe in no fixed law of development, causing all the "
               "inhabitants of a country to change abruptly...")  # truncated for brevity
    level = text_difficulty_level(content, d_difficulty_default)
    assert 4 <= level <= 8

# ----------------------------- 用户词汇难度测试 -----------------------------

def test_user_level_empty_dictionary():
    d_user = {}
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert level == 0

def test_user_level_one_simple_word():
    d_user = {'simple': ['202408050930']}
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert 0 < level <= 4

def test_user_level_invalid_word():
    d_user = {'xyz': ['202408050930']}
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert level == 0

def test_user_level_one_hard_word():
    d_user = {'pasture': ['202408050930']}
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert 5 <= level <= 8

def test_user_level_multiple_words():
    d_user = {
        'sessile': ['202408050930'], 'putrid': ['202408050930'], 'prodigal': ['202408050930'],
        'presumptuous': ['202408050930'], 'prehension': ['202408050930'], 'pied': ['202408050930'],
        'pedunculated': ['202408050930'], 'pasture': ['202408050930'], 'parturition': ['202408050930'],
        'ovigerous': ['202408050930'],  'orifice': ['202408050930'], 'aberration': ['202408050930'],
        'obliterate': ['202408050930'], 'niggard': ['202408050930'], 'neuter': ['202408050930'],
        'locomotion': ['202408050930'], 'lineal': ['202408050930'], 'glottis': ['202408050930'],
        'frivolous': ['202408050930'], 'frena': ['202408050930'], 'flotation': ['202408050930'],
        'ductus': ['202408050930'], 'dorsal': ['202408050930'], 'dearth': ['202408050930'],
        'crustacean': ['202408050930'], 'cornea': ['202408050930'], 'contrivance': ['202408050930'],
        'collateral': ['202408050930'], 'cirriped': ['202408050930'], 'canon': ['202408050930'],
        'branchiae': ['202408050930'], 'auditory': ['202408050930'], 'articulata': ['202408050930'],
        'alimentary': ['202408050930'], 'adduce': ['202408050930'],
    }
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert 6 <= level <= 8

def test_user_level_consider_only_most_recent_words_difficult_words_most_recent():
    d_user = {
        'pasture': ['202408050930'], 'putrid': ['202408040000'], 'frivolous': ['202408030000'],
        'simple': ['202408020000'], 'apple': ['202408010000']
    }
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert 5 <= level <= 8

def test_user_level_consider_only_most_recent_words_easy_words_most_recent():
    d_user = {
        'simple': ['202408050930'], 'apple': ['202408040000'], 'happy': ['202408030000'],
        'pasture': ['202408020000'], 'putrid': ['202408010000'], 'dearth': ['202407310000']
    }
    d_diff = get_difficulty_level_for_user(d_user, d_word_test)
    level = user_difficulty_level(d_user, d_diff)
    assert 3 <= level <= 5